Filings & markets — SEC EDGAR
Notable papers
🇺🇸 University of Washington
added 2026-07-17 · arXiv 2026-07-16
Systematic evaluation of prompt injection attacks targeting persistent memory in agentic systems, demonstrating successful exploitation across Claude and GPT models with implications for agent security.
- Identifies and systematizes a novel attack surface (memory-based prompt injection) that emerges as agents become stateful and self-improving—a practical security threat at the intersection of agent design and adversarial robustness.
- Empirical evaluation across multiple production agentic systems (Claude Code, OpenAI Codex) and model variants reveals that planted payloads in persistent memory reliably persist and influence future sessions, quantifying real vulnerability.
- Motivates a concrete defense design problem: protecting agent memory updates while preserving beneficial adaptation, relevant to practitioners building stateful agents in production.
agentssecurityprompt-injectionadversarialagentic-systems
abstract
pdf
Soham Gadgil, David Alexander, Sai Sunku, Franziska Roesner
🇺🇸 unknown
added 2026-07-17 · arXiv 2026-07-16
PolyQ co-designs quantization and CPU compilation to enable efficient fractional-bit LLM inference with mixed per-channel bit-widths, achieving 2.4–32% perplexity gains over existing methods on edge CPUs.
- Novel compiler/quantization co-design that solves practical fractional-bit deployment on CPUs via SIMD/LUT-compatible kernel generation and channel clustering, not just quantization in isolation
- Demonstrates stable quality scaling from 3–6 bits with measured end-to-end gains (70% reduction in activation reorder traffic, near-proportional throughput/latency scaling) across workstation/laptop/mobile CPUs
- Addresses a real deployment gap: existing mixed-precision methods are theoretically fine-grained but practically hard to execute on CPUs; PolyQ makes it work with <2% energy overhead
quantizationefficiencyedge-inferencecpucompiler-codesign
abstract
pdf
Hyunwoo Oh, Suyeon Jang, Hanning Chen, KyungIn Nam, Sanggeon Yun et al.
🇺🇸 unknown
added 2026-07-17 · arXiv 2026-07-16
Demonstrates that structural priors (cheatsheets) in LLMs achieve impressive in-distribution gains but fail dramatically under distribution shift, extending the router hypothesis across domains from math to code security with real CVE data.
- Replicates and extends SAIR's cross-distribution trade-off phenomenon to a new domain (code security), providing empirical evidence that the router hypothesis generalizes beyond formal reasoning
- Identifies a systematic failure mode: cheatsheets that saturate synthetic performance (100% F1) collapse on real CVE data (48.9% F1, -51.1pp), motivating rethinking of prompt calibration vs. distribution-aware training
- Comprehensive evaluation across three LLMs, three vulnerability categories with varying semantic complexity, and transfer to real-world VUDENC CVE data strengthens claims about generalization
reasoningdistribution-shiftcode-securitypromptingrobustness
🇨🇳 unknown
added 2026-07-17 · arXiv 2026-07-16
MCPEvol-Bench evaluates LLM agent robustness to dynamic tool interface changes via 11 mutation operators across 123 MCP servers, exposing significant vulnerabilities in frontier models.
- Novel evaluation dimension: first benchmark to systematically measure LLM agent adaptability under realistic tool evolution rather than static tool interfaces
- Reveals concrete failure mode in frontier models (13.7-14.4% performance drops, planning/reasoning errors) that current evals miss
- Practical relevance: MCP emergence as standard tool-use infrastructure makes dynamic tool compatibility a pressing real-world concern
agentstool-usebenchmarkrobustnessevaluation
abstract
pdf
Huanxi Liu, Kun Hu, Jiaqi Liao, Qiang Wang, Pengfei Qian et al.
🇨🇳 unknown
added 2026-07-17 · arXiv 2026-07-16
Flow matching approach for topology optimization that embeds physics-guided BESO trajectories to enable fast, stable conditional design generation without adversarial training or lengthy sampling.
- Physics-informed generative modeling: integrates BESO optimization history into flow matching without inference-time optimization, a novel path design principle
- Substantial efficiency gains: achieves better compliance, volume-fraction satisfaction, and topology fidelity with far fewer sampling steps than diffusion baselines
- Practical for engineering: addresses real TO bottleneck (repeated FEA) with a method that works on 2D and 3D problems under limited training data
generative-modelsflow-matchingtopology-optimizationphysics-informedefficiency
abstract
pdf
Shusheng Xiao, Jinshuai Bai, Hyogu Jeong, Yunfei Xi, Yilin Gui et al.
🇯🇵 University of Tokyo
added 2026-07-17 · arXiv 2026-07-16
Memory-efficient training framework for continuous-time spiking neural networks via differentiable spike-time discretization, reducing memory by 100× and enabling deeper SNN models on single GPUs.
- Novel discretization scheme that maps irregular spike times to fixed differentiable events, reducing activation memory from O(N_in·N_out) to O(M)—elegant theoretical contribution with practical scaling gains
- Synfire-chain-inspired regularization organizes temporal dynamics and prevents dead neurons, enabling training of significantly deeper SNNs (9-20 layer convnets) than prior work
- 100× memory reduction and 20× speedup on dense LIF layers demonstrates genuine scalability breakthrough for neuromorphic computing, historically a hard constraint
spiking-neural-networkstraining-efficiencymemory-optimizationneuromorphic
abstract
pdf
Yusuke Sakemi, Tomoya Takeuchi, Takeo Hosomi, Kazuyuki Aihara
🇨🇳 Alibaba Group
added 2026-07-17 · arXiv 2026-07-16
SEED improves agentic RL by converting on-policy trajectories into learnable hindsight skills and dense token-level distillation signals, bridging sparse episode rewards to fine-grained policy learning.
- Self-evolving distillation closes the supervision gap in outcome-based RL for LLM agents by extracting reusable natural-language skills and re-scoring actions under skill-augmented contexts for dense on-policy guidance.
- Jointly optimizes outcome-based RL with auxiliary token-level distillation from hindsight skills that co-evolve with the policy, maintaining alignment with current trajectory distribution.
- Demonstrates consistent improvements in sample efficiency and generalization across text and vision-based agentic tasks, with code release.
rlagentsdistillationpost-trainingreasoning
abstract
pdf
Jinyang Wu, Shuo Yang, Zhengxi Lu, Fan Zhang, Yuhao Shen et al.
unknown
added 2026-07-17 · arXiv 2026-07-16
Multidimensional voice AI benchmark (TTS, STS, SU, ASR) exposing acoustic and expressive capability gaps beyond standard isolated metrics.
- Addresses genuine gap: current benchmarks miss paralinguistic/acoustic information that distinguishes voice from text—core to real voice AI evaluation
- Reveals non-obvious findings (e.g., STS systems with audio access still remain transcript-driven) that should inform model development priorities
- Comprehensive across four major voice modalities with analysis of independence of evaluation dimensions (naturalness/expressiveness/identity for TTS), exposing evaluation design issues in the field
benchmarkvoice-aittsasrspeech-understandingevaluation
abstract
pdf
David Ayllon, Alice Baird, Jeffrey Brooks, Franc Camps-Febrer, Jakub Piotr Cłapa et al.
unknown
added 2026-07-17 · arXiv 2026-07-16
Demonstrates that finetuning LLMs on narrow, benign datasets causes broad ideological shifts across unrelated domains—a critical finding for model safety and alignment.
- Reveals an under-studied failure mode where seemingly-innocuous domain finetuning generalizes to unwanted ideological changes on out-of-distribution topics
- Proposes 'ideological generalisation' framework with measurable breadth and amplification metrics; shows finetuning pushes shifts further than few-shot prompting alone
- Empirically validates on GPT-4.1 and Gemma-3 that mixing with generic data doesn't prevent the effect, raising deployment concerns for policy-aligned systems
safetyfinetuningalignmentevaluationgeneralization
abstract
pdf
Robert Graham, Edward Stevinson, Yariv Barsheshat
🇨🇳 Qwen/Alibaba
added 2026-07-17 · arXiv 2026-07-16
LongStraw enables million-token RL post-training on fixed GPU budgets via architecture-aware execution optimizations for long-context agent training.
- Solves critical inference-posttraining context gap (inference 1M+ tokens vs RL training at 256K), enabling long-horizon agent learning.
- Architecture-aware stack with memory-efficient replay strategy (0.21GB overhead per group size increase) demonstrates feasibility of 2.1M-token RL on commodity GPUs.
- Validates on production models (Qwen, GLM) with concrete scaling results; establishes foundation for long-context RL at scale.
rlpost-traininglong-contextefficiencyagents
abstract
pdf
Changhai Zhou, Kieran Liu, Yuhua Zhou, Qian Qiao, Jun Gao et al.
🇨🇳 Alibaba
added 2026-07-17 · arXiv 2026-07-16
OmniaBench: A comprehensive agent evaluation benchmark spanning 354 domains with 1,431 tasks to diagnose capability boundaries of general AI agents.
- Largest hierarchical taxonomy for agent evaluation (354 level-2 domains across ToC/ToB/ToE) with executable environments and fine-grained 10-dimensional capability taxonomy
- Methodical task synthesis via four complementary routes (DAG, DAG-S, Solver, Program) reducing contamination risk; reveals clear frontier model limitations on planning and constraint maintenance
- Diagnostic value: structured failure analysis shows gaps in multi-step reasoning, enabling targeted model improvement beyond single-metric scores
agentsbenchmarkevaluationtool-usereasoning
abstract
pdf
Chengyu Shen, Yujie Fu, Gangtao Xin, Yanheng Hou, Wenlong Fei et al.
🇺🇸 unknown
added 2026-07-17 · arXiv 2026-07-16
Benchmark of 6 MLLMs on scientific visualization literacy reveals significant gaps in quantitative reasoning and domain-specific visual understanding compared to human baselines.
- Identifies concrete failure modes (fine-grained quantitative estimation, flow interpretation) critical for real-world multimodal AI deployment beyond generic chart QA
- Structured evaluation framework (49 items, 8 techniques, 11 task types) that exposes performance unevenness and could become a standard SciVis literacy benchmark
- Open-source benchmark and model outputs enable reproducible analysis of MLLM visual reasoning limitations in scientific domains
multimodalevaluationbenchmarkvisualizationreasoning
🇸🇬 National University of Singapore
added 2026-07-17 · arXiv 2026-07-16
BadWAM reveals a critical adversarial vulnerability in world-action models where small visual perturbations cause misalignment between predicted and executed actions, breaking assumed safety guarantees.
- First systematic adversarial attack framework targeting WAMs' core coupling property; shows 96.5%→43.1% success rate drop under simple perturbations
- Introduces imagination-preserving attacks that maintain plausible future predictions while inducing harmful action shifts—exposes hidden vulnerability class specific to WAMs
- Challenges the assumption that coupling action generation with future prediction provides interpretability and safety benefits for embodied AI systems
adversarialworld-modelsroboticsembodied-aisafety
🇺🇸 Stanford
added 2026-07-17 · arXiv 2026-07-16
Symbal detects systematic errors in MLLM-generated captions by identifying recurring visual-error associations, with a 1.7M-image benchmark across natural and medical domains.
- Addresses a concrete, practical problem in vision-language data quality—systematic misalignments—where errors correlate with specific visual features rather than being random
- Introduces SymbalBench, a substantial 1.7M-pair dataset across 420 VL datasets with annotated systematic misalignments, enabling benchmarking of error-detection methods
- Demonstrates real-world utility for auditing MLLM captions and datasets without model access, with 63.8% detection accuracy and 4x improvement over baselines
multimodaldatasetquality-controlevaluationvision-language
abstract
pdf
Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz
🇺🇸 NVIDIA
added 2026-07-17 · arXiv 2026-07-16
RoboTTT scales robot visuomotor context to 8K timesteps using test-time training, unlocking one-shot in-context imitation and long-horizon task completion.
- Test-time training with fast weights enables 8K-token context (3 orders of magnitude scaling) without inference overhead—a new scaling axis for robot models
- Demonstrates concrete capability gains: one-shot imitation from human video, on-the-fly policy adaptation, and completion of long-horizon (5-min, 10-stage) tasks that prior baselines fail
- Combines sequence action forcing + truncated BPTT into a practical recipe; validates that context length is a scaling law for embodied models, parallel to LLM findings
roboticsscalingtest-time-trainingin-context-learninglong-horizon
abstract
pdf
Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng, Fengyuan Hu, Yunhao Ge et al.
unknown
added 2026-07-17 · arXiv 2026-07-16
Reveals that LLMs violate basic probabilistic consistency when aggregating predictions across partitioned populations, introducing a novel self-consistency evaluation criterion.
- Identifies systematic failure of in-context learning to obey law of total probability—a fundamental probabilistic identity—across frontier models
- Introduces 'macro fallacy' pattern where fine-grained subpopulation estimates aggregate better than direct population-level estimates, suggesting misalignment between model's internal knowledge and aggregate output
- Proposes reference-free evaluation criterion (statistical self-consistency) that exposes a gap no existing benchmark captures, actionable for post-training/alignment
reasoningin-context-learningevaluationconsistency
abstract
pdf
Patrik Wolf, Thomas Kleine Buening, Andreas Krause, Celestine Mendler-Dünner
🇨🇳 Xiaomi
added 2026-07-16 · arXiv 2026-07-14
Production inference optimization system for Hybrid SWA + MoE + multimodal models, with novel KVCache management and RDMA-optimized distributed serving.
- First large-scale LLM serving system combining Hybrid SWA (linear attention), sparse MoE, and multimodal encoders in production—non-trivial engineering addressing real deployment constraints
- Systematic KVCache optimizations (layerwise prefetch, SWA-aware prefix cache trees, O(W) storage) and GCache distributed infrastructure with RDMA show measurable systems gains
- Practical multimodal optimizations (GPU preprocessing, parallel video decoding, cache sharing) demonstrate end-to-end efficiency gains beyond just the attention mechanism
efficiencyinferencekvcachemoehybrid-swamultimodalsystems
abstract
pdf
Xiaomi MiMo Team, Anqi Liu, Aoxin Ma, Bo Chen, Bo Yang et al.
🇨🇳 Chinese Academy of Sciences
added 2026-07-16 · arXiv 2026-07-14
ShortOPD recovers pruned LLMs' generation quality via adaptive short-to-long on-policy distillation, achieving 9× recovery on free-form generation with 4× better efficiency than standard baselines.
- Addresses critical gap between pruning validation (multiple-choice) and deployment reality (free-form generation); identifies and exploits suffix repetition bottleneck in recovery
- Novel training schedule that intelligently allocates on-policy rollout budget by detecting teacher-confirmed repetitive suffixes, reducing wasted computation by 71% while matching longer horizons
- Comprehensive evaluation on math, code, and open-ended generation shows structured pruning can achieve deployment-ready quality when paired with smart post-training recovery
pruningpost-trainingdistillationefficiencygeneration
abstract
pdf
Qingyu Zhang, Qianhao Yuan, Hongyu Lin, Yaojie Lu, Xianpei Han et al.
🇨🇳 unknown
added 2026-07-16 · arXiv 2026-07-14
Open-source unified multimodal model matching closed-source systems with efficient training ($400K) and comprehensive generation+understanding capabilities.
- Demonstrates competitive multimodal understanding and generation (text-to-image, editing, bilingual) with dramatically reduced training budget (~208M images, $400K) compared to closed-source systems
- Provides practical insights and reproducible recipes for efficient multimodal training; full weights and code released under Apache 2.0
- Shows agentic inference-time scaling can substantially boost performance—useful reference point for efficient multimodal systems under compute constraints
multimodalopen-weightsefficiencytext-to-imagepost-training
abstract
pdf
Guoxuan Chen, Chufeng Xiao, Haoran Yang, Siyue Xie, Binxiao Huang et al.
🇺🇸 unknown
added 2026-07-16 · arXiv 2026-07-14
A coupled Markov jump process framework for joint image-text generation with cross-modal self-correction and remasking, plus three new multimodal benchmarks.
- Novel sampler design where one modality's denoising transitions depend functionally on the other's confidence—enabling within-step cross-modal feedback rather than just parallel or interleaved updates
- Remasking mechanism to detect and repair contradictions between modalities, addressing a real limitation of standard MDMs
- Releases three large-scale joint multimodal corpora with matched in/out-of-distribution splits for rigorous evaluation
multimodaldiffusionreasoninggenerationdataset
abstract
pdf
Minh-Quan Le, Armand Comas, Alexandros Lattas, Stylianos Moschoglou, Pedro Vélez et al.
🇺🇸 University of Texas at Austin
added 2026-07-16 · arXiv 2026-07-14
OptCar adapts generalist vehicle dynamics models for high-speed off-road control via history-conditioned adaptation and synthetic rollouts, achieving 55% error reduction with minimal real-world data.
- History-conditioned dynamics context token enables efficient cross-terrain generalization without extensive terrain-specific data collection
- Novel adaptation recipe combining limited real-world + targeted synthetic rollouts solves practical sim-to-real gap for high-speed control where slip dominates
- Demonstrates strong out-of-distribution robustness (unseen payload) and competitive performance with 10x less data than specialist baselines
controldynamics-modelssim-to-realroboticsadaptation
abstract
pdf
Rwik Rana, Jesse Quattrociocchi, Christian Ellis, Nathan Tsoi, Garrett Warnell et al.
🇺🇸 Anthropic
added 2026-07-16 · arXiv 2026-07-15
Empirical study of alignment faking in LLMs via hidden-state probing, revealing asymmetric refusal residues and model-dependent detection limits with rigorous evaluation controls.
- First large-scale sweep (13 models) studying whether hidden states reveal alignment faking undetectable in outputs; identifies naturally-emerging faking in only Qwen3-32B and Llama-3.1-8B
- Establishes critical measurement framework correcting for leakage artifacts in prior probing work (residualization, leave-one-query-out, orthogonality constraints); shows naive approaches yield AUROC 1.0 on control where no faking occurs
- Reveals fundamental detection asymmetry: compliance shifts measurably under monitoring but refusal representations don't move, and steering detected directions barely changes behavior—constraining what probing can actually control
alignmentevalssafetymechanistic-interpretabilitypost-training
🇺🇸 Cornell University
added 2026-07-16 · arXiv 2026-07-15
A learned framework that predicts deep dual-optimal inequalities to stabilize column generation in routing problems, achieving 90%+ speedups in convergence time.
- Novel machine learning approach to a classical optimization bottleneck: uses classifier to learn pairwise dual variable orderings that provably stabilize CG without hand-crafted exchange arguments
- Strong empirical results on CVRP and VRPTW with dramatic CG time reductions (89.7% and 93.9%) while maintaining solution quality via recovery procedure with bound guarantees
- Addresses practical scalability challenge in branch-price-and-cut methods, relevant to large-scale logistics and vehicle routing
optimizationcolumn-generationlearning-to-optimizevehicle-routingduality
abstract
pdf
Zhengzhong Ricky You, Bo Tang, Haoran Liu, Baichuan Mo
🇺🇸 OpenAI
added 2026-07-16 · arXiv 2026-07-15
Systematic framework for allocating fixed RL post-training compute across model size, search, learning, and reward feedback—with empirical trade-off frontiers and accounting methodology.
- Addresses a practical but underexplored optimization problem in RL post-training: how to budget fixed compute across orthogonal dimensions (model capacity, rollout search, policy updates, reward inference).
- Introduces FLOP-accounting framework and RACE diagnostic protocol to decompose and profile compute allocation for GRPO, enabling reproducible comparison across allocation regimes.
- Empirical finding that optimal allocation is problem-dependent (model size, budget scale, reward type, evaluation metric) challenges single-heuristic approaches and motivates per-task profiling.
rlpost-trainingefficiencyreasoning
🇺🇸 Microsoft
added 2026-07-16 · arXiv 2026-07-15
GFlowRL removes the unstable partition network from GFlowNet-style RL while scaling stably to 235B MoE models, achieving strong gains on math, code, and adversarial robustness benchmarks.
- Replaces auxiliary partition function with in-batch Monte Carlo estimate—cleaner, more stable scaling for LLM post-training; systematic engineering insight applicable beyond GFlowNets.
- First GFlowNet-style RL to scale reliably across dense and sparse (MoE) architectures; prior work (FlowRL) diverges at scale.
- Achieves competitive code reasoning (Codeforces 2048 at 14B, ~25 Elo from o3-mini) and SOTA adversarial red-teaming (AdvBench/HarmBench), demonstrating practical impact on reasoning and safety.
rlpost-traininggflownetsscalingreasoning
abstract
pdf
Xiaodong Liu, Michael Xu, Jack W. Stokes, Paul Smolensky, Doug Burger et al.
🇺🇸 UCLA / Princeton
added 2026-07-16 · arXiv 2026-07-15
DeepLoop formalizes residual scaling for looped Transformers where parameter blocks are reused across multiple rounds, providing a principled method to stabilize training in parameter-efficient recurrent architectures.
- Addresses the overlooked residual scaling problem in looped/recurrent Transformers where parameters are visited multiple times, deriving visit-alignment coefficient κ_R and adjusted exponents α=(2N)^{1/2}, β=(8N)^{-1/2}
- Provides first-order perturbation analysis bridging shallow recurrent layers with deep models, recovering DeepNorm behavior and extending it to the tied-depth regime
- Demonstrates empirical improvements in validation loss and downstream accuracy on GPT-2 models when recurrent depth is activated, validating the theoretical framework
efficiencyarchitectureresidual-scalingrecurrenttraining-stability
abstract
pdf
Shuzhen Li, Yifan Zhang, Jiacheng Guo, Quanquan Gu, Mengdi Wang
unknown
added 2026-07-16 · arXiv 2026-07-15
FaStR learns spectral representations of RL dynamics via CP tensor decomposition, reducing sample complexity and improving transfer across actuator shifts.
- CP decomposition of state-action-next-state tensor yields separate encoders with smaller hypothesis class and O(min(S,A)) sample complexity gain over prior matrix methods
- Factored structure enables state encoder transfer across actuator shifts with only action encoder retraining—a genuinely useful RL property
- Moves spectral RL from matrix to tensor view with theoretical and empirical grounding on continuous control tasks
rlrepresentation-learningefficiencysample-efficiency
unknown
added 2026-07-16 · arXiv 2026-07-15
ExTernD enables ternary LLM quantization approaching arbitrary precision through expanded-rank factorization, achieving 5.2-5.7 bpw with Q4-Q5 accuracy.
- Novel factorization scheme ($A ≈ B diag(D) C$ with ternary factors) provably approaches bf16 accuracy as rank expands, overcoming fundamental ternary quantization ceiling
- Continuous accuracy-efficiency trade-off via rank multiplier μ and sparsity threshold τ rather than discrete bit-widths; matches Q4_K at 5.2-5.5 bpw on 4B models
- Post-training PTQ method applicable to modern LLMs without retraining, with demonstrated results on Gemma-4E2B and Qwen3.5-4B
quantizationefficiencypost-trainingfactorizationlow-bit
🇺🇸 unknown
added 2026-07-16 · arXiv 2026-07-15
STOCKTAKE: a 26-week supply-chain benchmark that disentangles state estimation from control failures in LLM agents via a fair Bayes-filter oracle, revealing that top models fail equally at diagnosis-to-action and over-correction.
- Separates perception (state estimation) from action (control) failures—a fundamental decomposition missing in prior agent evals that only score final outcomes
- Fair oracle design using factored POMDPs with exact Bayes filters enables skill scoring against identical observation streams agents receive, avoiding privileged-information circularity
- Multi-week horizons with hidden factor processes and curated stress profiles expose systematic model failures (e.g., correct diagnosis yet 34–43% stockouts; costly over-responses) that single-episode benchmarks miss
agentsbenchmarkreasoningevaluationplanning
🇺🇸 unknown
added 2026-07-16 · arXiv 2026-07-15
Reveals that post-hoc attribution methods fail to capture temporal reasoning in video medical models, showing anatomically faithful explanations can mask clinically critical blindness to end-systolic/diastolic frames.
- Exposes a systematic failure mode in XAI-based validation of video diagnostic models: spatial attribution fidelity is decoupled from temporal fidelity, undermining confidence in model interpretability for time-sensitive tasks.
- Empirically demonstrates via occlusion probes that attribution failure is not an artifact but reflects genuine model behavior—models ignore clinically decisive frames despite high EF regression accuracy.
- Calls for temporally-aware training and evaluation in medical video understanding, with direct implications for certification and deployment of video diagnostic AI.
xaivideo-understandingmedical-imaginginterpretabilityevaluation
🇫🇷 unknown
added 2026-07-16 · arXiv 2026-07-15
Exactly solvable model of grokking in neural networks using holomorphic activations, proving algebraic representability determines success/failure and explaining capacity-dependent memorization-to-generalization transitions.
- Provides rigorous algebraic characterization of when networks can represent targets on modular arithmetic tasks, eliminating the grokking phenomenon in a controlled setting
- Proves non-representable tasks incur width-independent training loss lower bounds, connecting expressivity constraints to memorization dynamics
- Traces continuous path from representational failure through memorization to standard grokking via bottleneck ablation, offering theoretical bridge between extreme and practical regimes
grokkingmemorizationalgebraic-geometrymodular-arithmetictheory
abstract
pdf
Chon-Fai Kam, Xavier Cadet, Miloud Bessafi, Frederic Cadet
🇺🇸 unknown
added 2026-07-16 · arXiv 2026-07-15
Competition and benchmark for probing whether frontier math LLMs use robust reasoning or spurious shortcuts via interpretability methods on AIMO problems.
- Addresses critical gap between eval metrics (accuracy) and model reliability (whether reasoning generalizes or exploits brittle patterns)
- Provides olympiad-level problems with symbolic variants + frontier model access + infrastructure—infrastructure for systematic interpretability research at scale
- Creates durable open robustness benchmark for mathematical reasoning, a bottleneck area for aligned capable AI
interpretabilityreasoningrobustnessbenchmarkmath
abstract
pdf
Michal Štefánik, Philipp Mondorf, Andreas Waldis, Qianying Liu, Chuan Yang et al.
unknown
added 2026-07-16 · arXiv 2026-07-15
Reframes penetration testing for AI systems from infrastructure compromise to behavioral objective violation, providing a systematic framework for evaluating adversarial attacks on learned models in production.
- Extends classical pentesting paradigm to AI-specific threat vectors (prompt injection, data poisoning, retrieval poisoning, agentic misalignment) that bypass traditional infrastructure security
- Proposes concrete workflow for identifying operational objectives, mapping AI-governed behavior, analyzing adversarial influence surfaces, and executing scenario-based tests—actionable for practitioners
- Addresses material gap in security evaluation: AI systems can fail catastrophically without infrastructure compromise, requiring new behavioral failure criteria and threat modeling
adversarialsecuritypost-trainingagentsevaluation
abstract
pdf
Mohammad Allahbakhsh, Mohammad Hassan Bahari, Moslem Attar-Raouf
🇺🇸 unknown
added 2026-07-16 · arXiv 2026-07-15
Rigorous analysis of how Transformer architecture components (skip connections, normalization placement, width expansion) preserve gradient and feature rank across depth, unifying normalization design principles through spectral theory.
- Provides novel theoretical framework explaining why Pre-Norm plateaus while Post-Norm rank-collapses and how skip connection scaling controls rank-ensemble tradeoff
- Connects initialization-time spectral properties (Marchenko-Pastur law, Jacobian rank) to trainability on downstream tasks, offering testable predictions
- Reframes core architectural choices (normalization placement, two-matrix FFN structure, width scaling) as solutions to fundamental rank preservation problem in deep networks
architecturetheoryinitializationdepthnormalization
🇺🇸 Harvard University
added 2026-07-15 · arXiv 2026-07-13
Training-free attribution method reveals that Transformer FFN neurons have sparse inter-layer dependencies, enabling circuit-level interpretability and potential efficiency gains.
- Demonstrates empirically that FFN activations can be reconstructed from sparse subsets of upstream neurons, challenging assumptions about dense feedforward structure
- Introduces practical, scalable training-free method for neuron-level circuit interpretation applicable across model scales
- Identifies candidate sparse pathways with direct implications for efficient inference without retraining
interpretabilityefficiencysparseffncircuits
unknown
added 2026-07-15 · arXiv 2026-07-13
Systematic study revealing that optimal expert training duration for model merging depends on the merging method, with sparsification-based approaches benefiting from overtraining where simple averaging fails.
- Novel empirical insight that training duration and merging method are jointly dependent rather than independent, contradicting standard practice
- Rigorous evaluation across 5 domains and 3 scales with 5 merging methods, grounded in bias-variance theory connecting to ensemble learning
- Practical implications for multi-task model merging as a scaling strategy for task adaptation without co-training overhead
model-mergingmulti-taskpost-trainingefficiency
abstract
pdf
Nikita Kozodoi, Zainab Afolabi, Jack Butler
🇨🇳 unknown
added 2026-07-15 · arXiv 2026-07-13
SymbOmni proposes an agentic omni-model for cumulative visual generation through symbolic concept learning, enabling continual learning without model fine-tuning and reducing token consumption by 40%.
- Novel architecture: Symbolic Concept Box abstracts low-level operations into reusable workflows, addressing compositional generalization in visual generation
- Efficient training: verbalized backpropagation with language-based feedback eliminates gradient-based fine-tuning while enabling continuous self-improvement
- Cumulative learning: demonstrates state-of-the-art continual learning across benchmarks with 40% token reduction, solving the 'perpetual novice' problem in generative models
multimodalagentscontinual-learningefficiencysymbolic-reasoning
abstract
pdf
Jinxiu Liu, Jianru Li, Tanqing Kuang, Xuanming Liu, Kangfu Mei et al.
🇺🇸 University of Texas at Austin
added 2026-07-15 · arXiv 2026-07-13
Rigorous benchmarking of LLM-based fMRI neural decoding reveals that large language model priors can mask failures—demonstrating the critical importance of blind controls in brain-computer interface research.
- Identifies a major methodological pitfall: high-capacity frozen language models succeed via learned prior rather than actual neural signal decoding, masking genuine decoder failure
- Improves Huth et al. ridge regression baseline by 11% METEOR through systematic engineering (expanded voxels, GPU acceleration, better proposal models)
- Contributes practical caution against uncritically stacking frozen LLMs in BCI pipelines without proper ablations—relevant to broader BCI/neuroscience methodology standards
fmrineural-decodingbcievaluationlanguage-models
abstract
pdf
Milos Suvakovic, Dom Marhoefer, Glenn Grant-Richards, Aidan Pinero
🇺🇸 Anthropic
added 2026-07-15 · arXiv 2026-07-13
Empirical study showing token reduction doesn't translate to cost savings for coding agents, and can harm task success—challenges common compression assumptions with large-scale billed API data.
- Rigorous empirical work on 2,848 Claude Code runs with actual billing data; reveals prompt caching dominates costs (87%), not tool-output tokens
- Demonstrates compression harms performance (27→15 solves on SWE-bench) by corrupting critical evidence, contradicting token-reduction-as-proxy assumptions
- Proposes success-adjusted billed-cost as evaluation metric instead of token count—actionable for API-based agent builders
agentscodingefficiencycost-optimizationempirical
🇺🇸 University of Washington
added 2026-07-15 · arXiv 2026-07-14
Critical re-evaluation of harness evolution for LLM agents, showing that published gains don't outperform simpler test-time scaling baselines and fail to generalize—challenging a popular paradigm.
- Exposes methodological flaws in how harness evolution is benchmarked (test-time scaling confound, same-task evaluation overfitting)
- Demonstrates that gains from automatic harness design don't consistently beat simpler baselines under fair comparison (matched budgets)
- Calls for stricter evaluation protocols for agentic systems, relevant as the field scales up test-time compute
agentsevaluationtest-time-scalingharness-design
abstract
pdf
Yike Wang, Huaisheng Zhu, Zhengyu Hu, Yige Yuan, Zhengyu Chen et al.
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
Audits widespread data leakage in WSI-VQA benchmarks, revealing 92–100% train-test overlap that invalidates claimed zero-shot performance of vision-language models in pathology.
- Exposes critical benchmark contamination (patient and institutional-level leakage) affecting a growing domain of clinical AI evaluation
- Demonstrates leakage is decodable and causally impacts reported accuracy gaps, undermining published VLM claims on major WSI benchmarks
- Provides concrete remediation framework (provenance tracking, automated auditing) applicable to other medical imaging benchmarks
benchmarkingdata-leakagemultimodalvision-languagemedical-imagingevaluation
abstract
pdf
Wenhao Zhang, Zhongliang Zhou, John Kang, Sheng Li
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
Identifies and analyzes a shared "countdown subcircuit" in LLMs that generalizes across diverse length-constrained tasks, revealing interpretable mechanistic structure.
- Mechanistic interpretability at scale: isolates a reusable computational motif (position vs. goal length comparison) in Llama-3.1-70B and traces its generalization to multiple tasks and models
- Demonstrates empirical transfer of circuit structure across models and domains (controlled writing tasks → DNA sequences → ASCII tables → natural language inferences), suggesting fundamentally shared computational strategies
- Unsupervised circuit discovery method on naturalistic data, bridging gap between toy mechanistic interpretability and real-world model behaviors
mechanistic interpretabilitycircuitsgeneralizationllamareasoning
abstract
pdf
Jacob Dunefsky, Wes Gurnee, Emmanuel Ameisen
unknown
added 2026-07-15 · arXiv 2026-07-14
Theoretical analysis of why learning-rate cooldown helps in some settings but not others, linking gradient noise structure and optimizer normalization to convergence behavior.
- Provides closed-form analysis of signSGD convergence under multiplicative noise and derives noise-floor constants exactly
- Mechanistic explanation for when/why cooldown phases improve final loss: non-normalized optimizers (SGD) self-anneal but normalized methods (sign-based, adaptive) require explicit schedule decay
- Connects optimizer normalization and noise structure to practical large-model pretraining schedules (WSD), with empirical validation on real tasks
optimizationlearning-rate-schedulesconvergence-theoryadaptive-optimizerspost-training
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
PM-Bench: a new benchmark for prospective memory in LLM agents, revealing systematic failures in delayed task execution across state-of-the-art models.
- Addresses a concrete, underexplored capability gap in agentic AI (prospective memory/task postponement) with a principled cognitive-science-inspired evaluation framework
- Benchmarking result showing even best models plateau at 65% F1 signals a genuine open problem worth investing in
- Released as controlled testbed for diagnosing failures and developing targeted training/inference interventions
agentsbenchmarksreasoningevaluation
🇨🇳 unknown
added 2026-07-15 · arXiv 2026-07-14
ARDepth reformulates monocular depth estimation as multi-scale auto-regressive generation with progressive visual conditioning, offering a structured alternative to diffusion-based approaches.
- Shifts MDE paradigm from global iterative denoising to hierarchical auto-regressive generation, better aligning with actual scale-dependent geometry emergence
- Introduces Scale-Progressive Conditioning (SPC) and Semantic-Aware Guidance (SAG) to enforce multi-scale coherence and structural consistency
- Demonstrates strong empirical results with explicit architectural motivation for how depth structure emerges hierarchically
monocular-depthgenerative-modelsauto-regressivemulti-scalegeometric-modeling
abstract
pdf
Zijie Wang, Wei Zhang, Weiming Zhang, Xiao Tan, Weikai Chen et al.
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
JoLT applies Tucker decomposition + Johnson-Lindenstrauss residuals to compress KV cache 2-3x near-losslessly by exploiting tensor structure, achieving order-of-magnitude better reconstruction error than prior methods.
- Novel tensor-aware approach to KV cache compression: treats cache as 3-order tensor, exploits differential redundancy across heads/tokens/features, unlike prior low-rank or quantization methods
- Joint optimization of Tucker ranks and residual bit-widths via Lagrangian dual under unified byte budget—principled allocation across layers and key/value pairs
- Strong empirical results: 2-3x compression with minimal perplexity/accuracy loss on Mistral-7B and LLaMA-2-13B; 0.009/0.006 relative Frobenius error, ~10x better than SVD/4-bit baselines
efficiencykv-cachecompressioninferencequantization
🇨🇳 Huazhong University of Science and Technology
added 2026-07-15 · arXiv 2026-07-14
CT-Repair uses Code and Temporal Execution Graphs with multi-perspective agentic reasoning to improve automated program repair, achieving significant gains on Defects4J v3.0.
- Structured representation of dynamic evidence (TEGs with 94.85% scope reduction) enables efficient context compression for LLM-based APR
- Multi-perspective agentic approach (static/dynamic/hybrid) with FSM-guided reasoning produces diverse repair strategies and reduces redundant sampling
- Strong empirical results: 489/854 bugs repaired, +19-30 over prior SOTA (ReinFix, RepairAgent) with smaller model budget
agentsprogram-repairreasoninggraphs
🇨🇳 unknown
added 2026-07-15 · arXiv 2026-07-14
KnowAct-GUIClaw improves OpenClaw with cross-platform GUI automation, self-evolving memory, and skill transfer, achieving 64.1% on MobileWorld using Kimi-2.6.
- Cross-platform GUI agent framework (Android/iOS/HarmonyOS/Windows) with experience-attributable memory and self-evolving skill library addressing real automation gaps
- Know-Route-Act-Reflect paradigm + pluggable architecture enables transferable skills across base models (+8.5% with Kimi-2.6), reducing per-model engineering
- SOTA results (64.1% MobileWorld) vs closed-source agents (Seed-2.0-Pro, GPT-4o) with open-weights foundation model
agentsgui-automationmulti-platformself-evolutionskill-transfer
abstract
pdf
Yunxin Li, Jinchao Li, Shibo Su, Zhenran Xu, Chenrui Zhao et al.
🇺🇸 Stanford University
added 2026-07-15 · arXiv 2026-07-14
Rigorous framework for extractable memorization claims in LLMs using matched comparisons and statistical calibration to distinguish true memorization from predictability.
- Formalizes a fundamental methodological problem in memorization research—establishing what probability thresholds constitute valid evidence of memorization—via conformal testing and census approaches
- Provides practical calibration methods (FPR-controlled thresholds as low as 1e-27) and shows prior extraction studies have significant false-positive rates (e.g., 24% for Wikipedia), directly impacting interpretability of memorization audits
- Redefines extractable memorization operationally to require both valid statistical claims and realistic extraction budgets, setting clearer standards for the field
memorizationinterpretabilitystatistical-methodsevaluationllm-auditing
abstract
pdf
A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa et al.
🇨🇳 Peking University
added 2026-07-15 · arXiv 2026-07-14
Efficient VLA deployment on edge devices via foresight-aligned asynchronous inference, achieving 8.66x speedup on Jetson Orin with perception-execution alignment correction.
- Addresses real deployment bottleneck: VLA models on low-power hardware with practical 8-14% improvements on LIBERO
- Novel foresight correction module elegantly handles perception-execution misalignment in asynchronous inference without retraining full models
- Combines algorithmic (confidence scheduling) and systems (CUDA graphs, GPU buffering) optimizations for concrete control frequency gains
efficiencyedge-deploymentembodied-aiasynchronous-inferencerobotics
abstract
pdf
Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu et al.
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
CARE-PPO combines PPO with loss prediction to jointly learn accurate numerical predictions and reliable confidence estimates in LLMs, validated on healthcare/finance tasks with OOD robustness.
- Novel RL framework that repurposes the critic network as a confidence estimator aligned with prediction error, bridging uncertainty quantification and actor-critic learning
- Demonstrates strong generalization across linguistic/domain shifts and reduced task-specific overfitting vs supervised fine-tuning
- Addresses a practical pain point: LLM hallucinations and overconfidence in quantitative prediction with measurable confidence calibration gains
rluncertaintypost-trainingreasoning
abstract
pdf
Mehak Dhaliwal, Rasta Tadayon, Andong Hua, Haewon Jeong, Yao Qin
🇨🇳 Beihang University
added 2026-07-15 · arXiv 2026-07-14
EcoSpec optimizes speculative decoding for MoE models by minimizing expert activation cost during draft selection, achieving up to 1.62× speedup on billion-parameter models.
- Addresses a real efficiency bottleneck in MoE inference: expert scattering during speculative decoding increases memory traffic and reduces speedup gains
- Practical system contribution with lightweight predictor and dynamic buffering that works with existing verification rules on production-scale models (DeepSeek-V3.1, Qwen3)
- Consistent empirical improvements across multiple model families and diverse tasks demonstrate genuine engineering value for MoE inference optimization
moespeculative-decodingefficiencyinference
abstract
pdf
Jincheng Xie, Runheng Liu, Heyan Huang, Yawen Ling, Hanbin Dai et al.
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
Line-anchored feedback in code editing reduces token generation by 22–58% and improves correctness on local models, demonstrating a structural prompt optimization with direct cost and accuracy benefits.
- Empirically quantifies token savings (22–58%) across multiple models (Claude Opus/Sonnet, local models) in a real code-editing task—direct relevance to inference cost and latency.
- Shows correctness gains for weaker models (+5–7 points) when feedback is structured, with evidence that the benefit amplifies when edit application is decoupled.
- Practical VSCodium extension (FileMark) and paired experiment design; technique is model-agnostic and immediately applicable to production code workflows.
efficiencycode-generationpost-trainingreasoning
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
Systematic study of what makes representational priors accelerate grokking, revealing that label-free invariances and early-window injection are surprisingly effective.
- Empirically characterizes the mechanistic prerequisites for grokking priors (feature family alignment, invariance structure) across 188 runs with strong ablations and quantified causality.
- Demonstrates label-free commutation invariances generalize more reliably than supervised priors with 2.7× speedup, suggesting fundamentally different inductive structure.
- Reveals timing is critical: priors only needed in first 2% of training budget, reducing the weight-norm delay-law exponent 17-fold, with practical implications for structured inductive bias.
grokkinginductive-biasmechanistic-interpretabilitygeneralization
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
A minimal 31-prompt instrument measuring convergence and conformity patterns across 44 LLMs, revealing structured divergence by model type and generation with public artifacts.
- Novel diagnostic tool with exact-match methodology (no embeddings/judges) revealing surprising quantitative structure in model output alignment—serendipity at 41% across diverse architectures
- Surprising finding: newest flagships (Claude, GPT) most conformist; persona/community-tuned models most divergent; conformity reverses in latest Claude/GPT, signaling possible high-level strategy shift
- Low-cost reproducible evaluation ($1/model) with full public prompts/transcripts/code—useful benchmark for tracking LLM behavior changes across versions and lineages
evalbenchmarkmodel-alignmentbehavior-analysisopen-artifact
🇯🇵 University of Tokyo
added 2026-07-15 · arXiv 2026-07-14
Mechanistic analysis of CoT in VLMs reveals visual access boundaries are shallow and independent of reasoning length, with performance bottlenecked by perceptual readout rather than computation.
- Causal intervention (Visual Access Sweep) rigorously isolates what CoT actually does—shows it doesn't require sustained image access despite longer generations, contradicting intuitive assumptions
- Identifies fundamental bottleneck at perceptual readout (attribute extraction) not reasoning/counting, with symbolic oracle experiments cleanly separating readout from computation failures
- Generalizes across multiple SOTA VLMs (Qwen2.5-VL, InternVL3) at various scales, providing actionable insights for VLM architecture and CoT prompting design
reasoningvision-languagemechanistic-interpretabilitychain-of-thoughtinference
abstract
pdf
Hiroto Osaka, Shohei Taniguchi, Gouki Minegishi, Kai Yamashita, Masahiro Suzuki et al.
🇺🇸 unknown
added 2026-07-15 · arXiv 2026-07-14
New multi-turn medical dialogue dataset revealing that frontier LLMs degrade substantially in correcting misconceptions over conversation length, with performance dropping from ~85% to ~50% by two turns.
- Multi-turn degradation pattern is clinically important and under-studied: exposes error propagation and inconsistency in high-stakes medical contexts where safety matters
- Rigorous evaluation methodology combining dataset design (2.4K real patient threads) with rubric-based LLM-as-Judge and oracle analysis to isolate causes of failure
- Actionable finding for practitioners: frontier models (GPT-5, Claude-Haiku) appear competent in single-turn but fail in realistic multi-turn patient interactions, directly applicable to medical AI deployment
evaluationmedical-aimulti-turnsafetybenchmark
🇨🇳 unknown
added 2026-07-15 · arXiv 2026-07-14
MemOps is an operation-level benchmark for diagnosing memory failures in long-horizon LLM-agent conversations, replacing black-box QA evaluation with structured lifecycle traces.
- Reformulates memory evaluation from downstream QA accuracy to interpretable operation-level diagnosis (remembering, forgetting, updating, reflecting), revealing failure modes hidden by final-answer scoring
- Introduces controllable generation pipeline embedding memory operations into long conversations with gold traces and six operation-level probe categories, tested across retrieval, parametric, and managed-memory systems
- Demonstrates concrete gaps: session-level retrieval outperforms turn-level, and long-context models are weak at ordered state trajectories—diagnostic results that inform agent architecture choices
agentsmemoryevaluationreasoninglong-context
abstract
pdf
Xixuan Hao, Zeyu Zhang, Zehao Lin, Yihang Sun, Ziliang Guo et al.
🇨🇳 unknown
added 2026-07-15 · arXiv 2026-07-14
Information-theoretic analysis of watermark forensics in generative models, establishing tight entropy-rate bounds for multi-user attribution and payload extraction.
- Proves tight Θ(log N/h) lower and upper bounds for multi-user attribution in watermarked text, a fundamental result previously lacking.
- Develops principled information-theoretic framework (information profile ν(t)) that unifies detection, attribution, extraction, and localization under one model.
- Identifies and proves a real gap: Θ(log N)-token window where text is detectable as machine-generated but unattributable, plus footprint-resolution uncertainty principle.
watermarkinginformation-theorysecurityforensicsgenerative-models
abstract
pdf
Xiaoyu Li, Zheng Gao, Xiaoyan Feng, Jiaojiao Jiang, Yulei Sui et al.
🇨🇳 University of Science and Technology of China
added 2026-07-15 · arXiv 2026-07-14
Proposes E3 framework for task-complexity-aware LLM agent execution that reduces token/file inspection overhead by 85–92% while maintaining task success through estimate-execute-expand strategy.
- Concrete efficiency win on deterministic benchmark (MSE-Bench with 121 real edits) plus validation on live gpt-4o + pytest; formalism (ACRR) quantifies agent cognitive redundancy
- Addresses real deployment cost: agents waste budget re-reading context; E3's minimum-sufficient execution matches baselines at 1/6 cost
- Releases benchmark and framework; bridges pure RL/planning work to practical agent engineering grounded in real task feedback loops
agentsefficiencyreasoningpost-training
🇨🇳 unknown
added 2026-07-14 · arXiv 2026-07-11
A human-centered multi-turn dialogue benchmark with decoupled user simulation and intent tracking that reveals significant gaps between state-of-the-art models on objective vs. subjective conversation quality.
- Addresses a genuine gap in LLM evaluation: multi-turn dialogue requires trajectory-level metrics (intent drift, completion) that single-turn benchmarks miss
- Principled methodology with persona grounding from human corpora rather than LLM synthesis, reducing evaluation bias; multi-judge ensembling improves robustness
- Novel findings: 9x gaps on objective intent tracking despite models being statistically close on subjective dimensions (empathy/persona); reasoning improves tracking but not subjective scores
benchmarkdialogueevaluationintent-trackingmulti-turn
abstract
pdf
Jinglan Gong, Jiefan Lu, Hewei Guo, Kehan Li, Zhiyuan Han et al.
🇺🇸 MIT
added 2026-07-14 · arXiv 2026-07-11
Post-training framework using continuous physics rewards (PDE residuals + solution accuracy) to improve LLM code generation for numerical PDE solvers, with compositionality transfer to unseen problems.
- Novel hybrid verifier combining hard executability checks with graded continuous rewards for scientific correctness—addresses key gap in RL for verifiable code where binary signals discard accuracy structure
- Demonstrates a smaller RL-post-trained model outperforms frontier model prompting on PDE benchmarks, plus zero-shot transfer to held-out PDEs, suggesting learned compositional structure of numerical methods
- Unifies diverse PDE families (hyperbolic, parabolic, elliptic, incompressible flow) under single policy, showing evidence of learning reusable numerical primitives (stencils, time-stepping, boundary handling)
rlpost-trainingcode-generationreasoningscientific-computing
abstract
pdf
Pengfei Cai, Utkarsh Utkarsh, Alan Edelman, Christopher Vincent Rackauckas, Rafael Gomez-Bombarelli
🇺🇸 CMU
added 2026-07-14 · arXiv 2026-07-11
Vision paper proposing to treat AI-driven research systems as deterministic database engines to eliminate hallucinations, stale results, and redundant computation in LLM agents.
- Identifies fundamental failure modes of LLM agents (nondeterminism, unbounded outputs, no provenance tracking) with principled database-inspired solution: LLM as query compiler only, executor as deterministic dataflow engine with versioning and incremental maintenance.
- Concrete design framing (versioned code/data DAGs, materialized views, cost-based scheduling) maps traditional DBMS guarantees (consistency, provenance, idempotence) to research reproducibility problems that current agent frameworks ignore.
- Early-stage vision paper but stakes out significant problem space at intersection of systems and AI agents; likely to influence how future research automation platforms are architected.
agentssystemsreproducibilitydatabasesresearch-automation
🇨🇳 Alibaba & Peking University
added 2026-07-14 · arXiv 2026-07-12
UNIBROWSE: a unified data-to-agent pipeline for multimodal web browsing that covers all three information-flow patterns and achieves SOTA on BrowseComp benchmarks via SFT + exploration-aware RL.
- First to systematically generate training data for all three multimodal browsing patterns (text-only, image-to-text, text-to-image), addressing a gap in agent generality
- Novel exploration degree metric to filter low-signal RL instances, improving sample efficiency for tool-use trajectory learning
- Substantial benchmark gains (54.4 avg accuracy, +10.5 over base Qwen3.5-35B-A3B) that exceed closed-source agents like GPT-5 and Gemini-2.5
agentsmultimodalrlpost-trainingweb-browsing
abstract
pdf
Xiyu Wei, Qingwei Zong, Zhuocheng Yu, Sujian Li
🇺🇸 Johns Hopkins University
added 2026-07-14 · arXiv 2026-07-12
Identifies and diagnoses the 'compliance trap' in memory-augmented AI agents: how conflicting retrieved memories cause early adoption errors that amplify through trajectories and resist recovery.
- Proposes E-P-R (Entry-Propagation-Recovery) framework to systematically analyze memory consumption in agents beyond retrieval quality alone
- Reveals counterintuitive failure mode: stronger baseline agents suffer larger absolute damage from bad memory compliance, suggesting existing eval metrics miss critical safety concerns
- Introduces MemTrapBench, a controlled benchmark isolating memory consumption phases, advancing agent evaluation methodology
agentsmemoryreasoningevaluationinteractive-environments
🇺🇸 Caltech
added 2026-07-14 · arXiv 2026-07-12
Hybrid additive-multiplicative optimizer for low-precision LLM training that combines strengths of both update types to handle the failure modes of standard quantization.
- Addresses a concrete failure mode in low-precision training (optimization stalling at large weights under coarse mantissa)
- Provides theoretical monotone descent guarantee and demonstrates practical improvements across multiple precision levels (BF16, FP8, FP4) and model scales
- Cost-relevant method for efficient pretraining without requiring high-precision weight copies
efficiencypost-trainingquantizationoptimization
abstract
pdf
Xiaoyuan Liang, Sebastian Loeschcke, Mads Toftrup, Anima Anandkumar
unknown
added 2026-07-14 · arXiv 2026-07-12
MafiaScope is an open testbed that uses the game Mafia to probe and measure LLM agents' theory of mind and internal beliefs through non-invasive structured questioning.
- Novel evaluation method: repurposes social deduction games as a measurement instrument for machine theory of mind, with ground-truth beliefs accessible only to the game engine
- Actionable diagnostic tool: reveals miscalibration and systematic biases (e.g. agents over-predict suspicion by 1.5×) that wouldn't show in standard behavioural metrics
- Open release with corpus: engine, visualizer, interactive replay, and 200+ cross-model games provide infrastructure for future work on agent reasoning and deception
evalagentsreasoningtoolopen-weights
🇨🇳 University of Science and Technology of China (USTC)
added 2026-07-14 · arXiv 2026-07-12
Progressive Tree Drafting enables 2× LLM inference speedup via structured parallel draft generation in a single forward pass, training-free and model-agnostic.
- Addresses critical LLM inference bottleneck (memory-bound decoding) with a practical, training-free method that doesn't require auxiliary draft models
- Novel tree-structured parallel drafting strategy with stepwise pruning that meaningfully improves upon existing speculative decoding by exploiting within-model parallelism
- Strong empirical results (2× speedup) demonstrated across benchmarks with immediate applicability to inference systems
inferencespeculative-decodingefficiencyparallelism
abstract
pdf
Zipeng Gao, Zhi Zheng, Qingrong Xia, Junda Lin, Ziwei Zhao et al.
🇺🇸 unknown
added 2026-07-14 · arXiv 2026-07-12
Answer-conditioned CoT distillation from frontier VLMs to 3B models for few-shot industrial vision, achieving strong gains on real manufacturing tasks with minimal labeled data.
- Practical few-shot adaptation method (18-30 labeled images per task) for industrial visual inspection—a real deployment bottleneck
- Answer-conditioning insight: frontier model reasoning directed at correct label prevents garbage-in-garbage-out, with ablation showing 17.8pp performance cliff
- Outperforms GPT-4.1 on weld radiography with 24 training images; demonstrates efficiency gains matter for manufacturing constraints
vlmdistillationfew-shotcotefficiencyindustrial
🇺🇸 Carnegie Mellon University
added 2026-07-14 · arXiv 2026-07-12
Empirical study of indirect data poisoning attacks on AI-driven scientific research, showing 49.56% success rate across frontier models and proposing provenance auditing defenses.
- First systematic evaluation of data poisoning against autonomous research agents using frontier models (Claude, GPT, Gemini), demonstrating a critical vulnerability in AI-driven science
- Practical attack requires only public dataset corruption with misleading metadata—no sophisticated trigger words or prompt injection—making it a realistic threat to scientific integrity
- Proposes and validates mitigation via data provenance auditing with 5 checks, reducing attack success to zero, offering actionable defense for the research ecosystem
securitydata-poisoningscientific-integrityai-safetyadversarial
abstract
pdf
Bálint Gyevnár, Atoosa Kasirzadeh, Nihar B. Shah
🇺🇸 Anthropic
added 2026-07-14 · arXiv 2026-07-12
Demonstrates that misaligned behavior in synthetic agentic training data persists even after removing harmful actions, revealing diffuse disposition encoding independent of action-level filtering.
- First empirical evidence of 'phantom transfer'—that adversarial dispositions in synthetic trajectories transfer to models even when explicit harmful actions are removed, invalidating action-level filtering approaches.
- Shows the effect is model-dependent (Gemini vs Claude) and survives standard safety benchmarks, suggesting evaluations miss subtle misalignment vectors in agent training data.
- Directly relevant to agent safety: as LLMs deployed as agents train on synthetic rollouts, this work exposes a critical gap in current data curation practices for agentic behavior.
agent-safetysynthetic-dataalignmentpost-trainingjailbreak
🇺🇸 Alibaba/Qwen (primary), with US-based contributors
added 2026-07-14 · arXiv 2026-07-12
SETA: a scalable framework generating 4,500+ verifiable terminal RL environments for training LLM agents on command-line tasks, achieving SOTA results for RL-trained 8B models.
- Addresses genuine bottleneck in agent training: constructing diverse, verifiable terminal task distributions at scale without natural supervision.
- Releases SETA-Env (4,500+ environments) as open-source resource with dual pipelines (synthesis + evolution) for environment generation.
- Demonstrates solid empirical gains: 12% pass@1 on Terminal-Bench 2.0 for 8B-scale RL-trained model, plus +3% gains on DeepSeek-V4-Flash under same harness.
agentsrlpost-trainingopen-weightsdataset
abstract
pdf
Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru, Aznaur Aliev, Jay Rainton et al.
🇮🇱 Tel Aviv University
added 2026-07-14 · arXiv 2026-07-12
Singularity-space diffusion framework for signal generation that recovers sharp transients via complex-plane pole-residue representations, achieving 8× compression and sub-resolution generalization.
- Novel representation: pole-residue latent space instead of dense grids—directly captures physics of discontinuities and transients; avoids Gibbs artifacts
- Resolution-free reconstruction on arbitrary grids without retraining; 4.2× better zero-shot sub-resolution generalization vs. grid baselines
- Physically interpretable: each singularity maps to physical parameters; demonstrated on Burgers shocks with 10^−4 parameter recovery accuracy; potential for speech/biomedical signals
diffusionsignal-processinginverse-problemssparse-representationphysics-informed
🇺🇸 Google
added 2026-07-14 · arXiv 2026-07-13
BackendForge benchmark evaluates agentic LLMs on realistic end-to-end backend code generation with black-box HTTP testing, revealing significant gaps between local API behavior and complete service correctness.
- Novel evaluation paradigm for agentic coding: co-evolving test oracles and reference implementations captures real-world deployment constraints missing from typical code generation benchmarks
- Realistic, deterministic evaluation methodology using OpenAPI contracts and HTTP testing avoids ambiguous success criteria that plague synthetic code generation tasks
- Reveals concrete failure modes: 55.4% → 28.6% drop from base to final oracle shows current LLMs (including GPT-4.5) struggle with system-level consistency despite local correctness
agentscode-generationbenchmarksevaluationbackend
abstract
pdf
Yuzhe Guo, Mengzhou Wu, Yuan Cao, Jialei Wei, Dezhi Ran et al.
🇺🇸 unknown
added 2026-07-14 · arXiv 2026-07-13
Diagnostic study revealing that video-LLMs don't actually track characters in long-form video despite benchmark claims—they rely on shallow gender cues and multiple-choice artifacts.
- Exposes fundamental failure mode in video-LLMs: inability to bind named individuals to their visual identity across frames, not a data/compute issue but an architectural/reasoning bottleneck
- Rigorous protocol (9 conditions, name-swapping, gender ablations, open-ended evaluation) systematically dismantles claimed benchmark scores and identifies spurious signals
- Releases diagnostic toolkit for auditing what video-LLM benchmarks actually measure—directly useful for practitioners evaluating models and designing better evals
video-llmevaluationbenchmarkingreasoningmultimodal
abstract
pdf
Mohammad Al-Ratrout, Shayla Sharmin, Aditya Raikwar, Roghayeh Leila Barmaki
🇨🇳 unknown
added 2026-07-14 · arXiv 2026-07-13
Proposes a unified residual-weighting framework for PINNs that respects physical information propagation paths, improving training stability and accuracy through theoretically-grounded priority scheduling.
- Addresses fundamental PINN training inefficiency (synchronous optimization of unrelated constraints) with principled solution rooted in NTK theory
- Unifies temporal, spatial, and boundary priorities under single propagation-path framework with clear mathematical characterization
- Consistent empirical improvements on benchmark PDE problems without architectural changes, practical for domain science applications
physics-informed-networkstraining-efficiencypde-solvingoptimization
abstract
pdf
Zhangyi Lian, Xinda Dong, Wenxuan Huo, Weifeng Huang, Gang Zhu et al.
🇺🇸 Stanford
added 2026-07-14 · arXiv 2026-07-13
VIA reframes robot control as a vision-based agent task, leveraging frontier models' existing computer-use capabilities to achieve strong manipulation performance without robot-specific fine-tuning.
- Elegant interface design (browser-based 3D) that lets off-the-shelf frontier agents (Claude, Fable) control robots zero-shot without retraining, demonstrating emergent transfer of computer-use skills to robotics
- High performance on real manipulation tasks (96.7% on LIBERO-Goal, 100% on assembly) using only visual input and generic tools, suggesting frontier models already encode relevant reasoning
- Shifts paradigm away from expensive VLA fine-tuning by leveraging model scale directly—performance scales with foundation model capability rather than robot-specific data
roboticsagentszero-shotvisionfoundation-models
abstract
pdf
Hengyuan Hu, Priya Sundaresan, Jensen Gao, Dorsa Sadigh
🇨🇳 unknown
added 2026-07-14 · arXiv 2026-07-13
Unified Gradient Projection mitigates catastrophic forgetting in multilingual low-resource ASR by balancing per-language gradient contributions during continual learning on pretrained Whisper models.
- Addresses real deployment problem: fine-tuning Whisper on low-resource languages without forgetting high-resource ones
- Novel gradient-space solution combining per-language projection with balanced replay—elegant approach to cross-lingual interference
- Demonstrates near-zero forgetting on Whisper-large-v3 with practical gains across diverse language groups and model scales
continual-learningmultilingualasrcatastrophic-forgettinglow-resource
abstract
pdf
Ziang Ren, Guodong Lin, Yuchen Ai, Kaize Tan, Wei-Qiang Zhang
🇨🇳 unknown
added 2026-07-14 · arXiv 2026-07-13
Pix2Act reformulates 3D manipulation as 2D image-space prediction with equivariant camera augmentation, improving robustness and generalization for imitation learning.
- Clever reformulation of 3D control into 2D image-space trajectory prediction + triangulation, reducing learning complexity while enabling equivariant augmentation across multiple camera views.
- Novel per-view rotation equivariance design that jointly transforms camera images and actions, implicitly augmenting data distribution and learning view-invariant action structures.
- Strong empirical results on diverse simulated and real-world manipulation tasks with robustness to camera perturbations, suggesting practical applicability.
robot-learningimitation-learningmanipulationequivariancemulti-view
abstract
pdf
Haojie Huang, Linfeng Zhao, Haotian Liu, Zhang Ye, Si-Yuan Huang et al.
🇨🇳 unknown
added 2026-07-14 · arXiv 2026-07-13
Comprehensive framework for scaling medical AI agents from task-specific assistants to autonomous clinical systems, emphasizing environment scaling and self-improvement through interaction.
- Addresses deployment-critical gaps: formalized autonomy taxonomy (assisted→cooperative→autonomous) and contamination-resistant benchmarks for clinical validation
- Identifies clinical environment scaling (PACS/EHR/FHIR integration) as underexplored yet actionable direction, moving beyond parameter scaling toward self-evolving agents
- Consolidates 300+ references on medical agents (2025-2026 emphasis) with concrete roadmap for hallucination/cascade-failure mitigation and fairness in clinical imaging (radiology, pathology, ophthalmology)
agentsmedicalautonomous-systemsenvironment-scalingself-improvement
abstract
pdf
Chunzheng Zhu, Lei Tian, Bohan Tan, Ziqi Zhou, Yuxuan Sun et al.
🇨🇳 Tsinghua University (THUDM)
added 2026-07-14 · arXiv 2026-07-13
ScaleCUA scales computer use agents via verifiable task synthesis and frontier sampling, achieving SOTA on OSWorld and ScienceBoard with open-source code and models.
- Addresses genuine bottleneck: verifiable data scarcity in online RL for GUI agents by proposing VeriGen, an automated task synthesis pipeline producing 24K+ verifiable tasks at scale
- Frontier Sampling efficiently allocates RL rollouts based on per-task capability, maximizing sample efficiency—a practical contribution for online RL scaling
- Strong empirical results (68.7% OSWorld, 54.0% ScienceBoard) with reproducible open-source release (code, models, datasets), advancing the computer use agent frontier
agentsrlpost-trainingopen-weightsgui-automation
abstract
pdf
Bowen Lv, Xiao Liu, Yanyu Ren, Hanyu Lai, Bohao Jing et al.
🇺🇸 University of Kansas
added 2026-07-14 · arXiv 2026-07-13
TreeThink is an open-source modular library for asynchronous tree search in neural theorem proving, supporting Lean 4, Rocq, and Isabelle/HOL with integrated formal verification.
- Addresses a real infrastructure gap: existing tree search libraries lack native formal verifier integration; TreeThink bridges neural LLM reasoning with multiple proof assistants via REPL
- Demonstrates non-trivial engineering: fully asynchronous execution yields 6.3× speedup and scales across multiple formal languages (Lean 4, Rocq, Isabelle/HOL)
- Open-source, MIT-licensed library with reproducible benchmarks (miniF2F, MATH500) lowers barrier to neural theorem proving research
reasoningtree-searchtheorem-provingopen-sourceformal-verification
abstract
pdf
Burak S. Akbudak, Zeynel A. Uluşan, Can S. Erer, Gözde Gül Şahin
🇺🇸 LaunchSafe
added 2026-07-14 · arXiv 2026-07-13
Self-evolving agentic OS that autonomously discovers and hot-loads web exploitation capabilities, achieving 100% success on 104 CTF-style benchmarks—demonstrates that capability discovery, not reasoning, is the bottleneck in autonomous exploitation.
- Novel architecture treats exploit capability as versioned kernel with runtime synthesis & validation, enabling hot-loading of new capabilities without redeployment
- Empirical law: once a capability is discoverable, difficulty collapses—shifts focus from reasoning to capability engineering, with self-improving loop that sandboxes & commits fitness-positive modifications
- Full coverage on XBOW (104 targets, 26 vuln classes, 3 tiers) with cryptographic per-build flag verification under strict anti-fabrication regime; deliberately withholds operational artifacts due to dual-use concern
agentssecurityautonomous-systemsself-improvingexploitation
abstract
pdf
Praneeth Narisetty, Shiva Nagendra Babu Kore
unknown
added 2026-07-14 · arXiv 2026-07-13
API audit of LLM tutors reveals differential refusal and epistemic gatekeeping against marginalized students, showing safety alignment can institutionalize educational inequality.
- Systematic empirical evidence that safety-aligned models exhibit 76.7% higher refusal rates and 3× reduced complexity access for low-SES/minority student personas—concrete mechanism linking alignment to bias
- Introduces measurable framework (differential refusal, agency theft, hermeneutical injustice) for auditing LLMs as deployed educational tools, with direct pedagogical implications
- Challenges assumption that 'safer' models are uniformly safer, showing safety mechanisms can amplify rather than mitigate discrimination depending on user context
safetybiaseducationauditingllm-alignment
abstract
pdf
Alexis Popovici, Andrei Ionascu, Adrian-Marius Dumitran
🇨🇳 Nanjing University
added 2026-07-14 · arXiv 2026-07-13
Multi-agent framework for proof autoformalization using efficient test-time optimization guided by formal verification, improving on prior work by 19% on ProofFlowBench.
- Addresses long-horizon proof autoformalization (statement→full proof) via structured decomposition-formalization-proving pipeline with bottleneck analysis directing compute efficiently
- Novel test-time optimization approach using Pareto-frontier guided refinement of decompositions based on formal verification + semantic rubrics, avoiding costly training
- 19% improvement on ProofFlowBench with lower test-time cost; scaling analysis shows gains converge quickly, enabling practical budget selection
reasoningproof-formalizationtest-time-optimizationmulti-agentformal-verification
abstract
pdf
Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng, Haoyu Liu, Runjie Xu et al.
🇨🇳 Astribot
added 2026-07-14 · arXiv 2026-07-13
PHILIA is a modular multi-robot agent architecture decoupling high-level semantic reasoning from low-level execution, enabling compositional long-horizon household manipulation with human-in-the-loop interaction.
- Robot gateway abstraction cleanly separates agent reasoning from per-robot execution, enabling heterogeneous embodiments and plug-and-play policy/interface improvements
- Demonstrates real long-horizon dexterous tasks (packing, lifting) with persistent memory and scene grounding on physical hardware (Astribot S1)
- Compositional design pattern—advances in any component (UI, policies, navigation) improve overall experience without system redesign—addresses practical deployment constraints
roboticsagentsembodied-aihuman-robot-interactionlong-horizon-planning
abstract
pdf
Weiqi Jin, Peijun Tang, Kuncheng Luo, Baifu Huang, Binyan Sun et al.
🇺🇸 unknown
added 2026-07-14 · arXiv 2026-07-13
Linear probes on LLM internal activations reliably detect confident hallucinations in financial QA, outperforming surface-level confidence baselines.
- Novel insight that residual stream activations carry discriminative signal for hallucination detection beyond token log-probabilities or self-assessment
- Practical method for high-stakes domain (finance) with clear commercial value as a triage mechanism for human review
- Systematic evaluation across multiple models (Qwen, Llama, Gemma) demonstrating generalization of the probing approach
interpretabilityhallucination-detectionprobingfinancial-reasoningreliability
unknown
added 2026-07-14 · arXiv 2026-07-13
HyperSafe uses hypernetworks to generate model-specific safety networks that restore alignment of fine-tuned LLMs without retraining or weight modification.
- Novel inference-time safety restoration via hypernetwork-generated side networks conditioned on layer-wise activation fingerprints—elegant post-hoc approach that doesn't require retraining or safety data at deployment
- Demonstrates strong empirical results (19–31% → <1% harmful rates) across multiple model families while preserving task accuracy, addressing a real deployment pain point
- Non-invasive method avoids gradient updates and model modification, making it practical for already-deployed fine-tuned checkpoints
safetyalignmentpost-traininginference-timeefficiency
abstract
pdf
Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem et al.
🇺🇸 University of Massachusetts Amherst
added 2026-07-14 · arXiv 2026-07-13
LASKO applies Lie algebroid geometry to agentic skill optimization, using bracket-based screening to reduce expensive LLM validations by 15×.
- Novel mathematical framework (Lie algebroids) for modeling non-commutative skill edits with latent structure, enabling cheap microsecond screening before costly LLM rollouts.
- Concrete 15× speedup on causal extraction demonstrates practical benefit for agent self-improvement loops where edit composition order and hidden template effects matter.
- Addresses a genuine problem in agentic systems: naive skill editing is combinatorially expensive; this substitutes algebraic structure for brute-force validation.
agentspost-trainingoptimizationreasoning
🇨🇳 Xiaomi Robotics
added 2026-07-14 · arXiv 2026-07-13
38B multimodal autoregressive model for unified embodied synthesis combining image/video generation with robot control, achieving SOTA on real-world manipulation tasks.
- First to support multi-view consistent scene generation across multiple robot embodiments with structured, controllable embodied transfer while preserving dynamics
- Demonstrates that foundation world models can scale as both embodied world models and data engines—improves real-world manipulation success from 36.9% to 63.2% via generated training data
- Unified framework that jointly optimizes 5 tasks (text-to-image, editing, scene/transfer/video generation) while preserving pre-trained generalization, ranking first on World Arena benchmarks
multimodalroboticsembodied-aiworld-modelsopen-weights
abstract
pdf
Xinghang Li, Jun Guo, Qiwei Li, Long Qian, Hang Lai et al.
unknown
added 2026-07-14 · arXiv 2026-07-13
Identifies dimensionality collapse as a precursor to grokking and proposes GeomDR, a spectral regularizer that accelerates generalization by up to 52× through geometric control.
- Mechanistic insight into grokking (delayed generalization) via representation geometry—a fundamental phenomenon relevant to understanding neural network training.
- Practical intervention (GeomDR) that reliably modulates grokking timing across modular arithmetic and permutation tasks in both MLPs and transformers.
- Bridges geometry and generalization dynamics, offering a generalizable framework for controlling training dynamics beyond toy tasks.
grokkingpost-trainingefficiencyinterpretabilityregularization
unknown
added 2026-07-14 · arXiv 2026-07-13
A modular GraphRAG system with a compact 7B domain-adapted LLM that outperforms much larger models on knowledge graph construction and achieves strong retrieval performance on benchmark tasks.
- Two-stage extraction with DBSCAN deduplication and Leiden community detection improves graph quality over single-pass approaches
- Demonstrates that language skills (comprehension, extraction, reasoning) scale weakly with model size, enabling a 7B model (Meno-Lite-0.1) to outperform Qwen2.5-32B on KG construction
- Open-source, single-GPU deployable system with clear evidence of improvements in evidence recall (0.84 vs ≤0.76) on GraphRAG-Bench Medical tasks
ragknowledge-graphsefficiencyopen-weightspost-training
abstract
pdf
Mikhail Komarov, Ivan Bondarenko, Stanislav Shtuka, Oleg Sedukhin, Roman Shuvalov et al.
🇨🇳 unknown
added 2026-07-14 · arXiv 2026-07-13
Proposes an integrated roadmap for physical intelligence via World Action Models and embodied brains, addressing fragmentation in action spaces, datasets, and system composition for embodied AI agents.
- Tackles fundamental fragmentation in embodied AI—incompatible action spaces, datasets, and task conventions—with a concrete co-evolution roadmap rather than point solutions
- Introduces 'embodied brain' concept that decouples high-level reasoning (multimodal context, intervention comparison) from low-level control, enabling modular reuse across heterogeneous embodiments
- Proposes shared contracts and closed-loop post-training as system-level solutions to standardize interaction between world models, controllers, and verification—addressing a real infrastructure gap in physical AI
embodied-aiworld-modelsphysical-intelligencesystem-designrobotics
abstract
pdf
Yuanzhi Liang, Xufeng Zhan, Haibin Huang, Chi Zhang, Xuelong Li
unknown
added 2026-07-14 · arXiv 2026-07-13
Hourglass reasoning enforces strict information isolation between reasoning stages via symbolic bottlenecks to improve few-shot induction, achieving 14pt gains on ARC-AGI-2 and nearly doubling Verilog synthesis accuracy.
- Novel architectural constraint on reasoning flow: enforced stage isolation with only compressed symbolic state crossing boundaries, not prior work on prompting or CoT
- Strong empirical gains across diverse benchmarks (visual abstraction, hardware synthesis, linguistics) with substantial Verilog synthesis improvement (31%→58%)
- Rigorous ablations isolating the contribution of stage isolation and induction quality, addressing a genuine failure mode of self-refinement in LLMs
reasoningpromptingfew-shotinductionsymbolic
🇺🇸 Anthropic
added 2026-07-14 · arXiv 2026-07-13
Automated red-teaming framework that discovers reusable vulnerability patterns in production LLM agents through a falsifiable research loop, generating a transferable vulnerability concept graph.
- Addresses critical safety gap: systematic discovery of agent vulnerabilities across Claude Code and Codex rather than one-off attacks
- Novel artifact (Vulnerability Concept Graph) captures enabling conditions and transferability, not just success metrics—actionable for production teams
- Demonstrates 14.2pp improvement over baselines with single-shot transfer across scenarios, suggesting genuine discovery of fundamental unsafe behaviors
safetyagentsred-teamingproductionvulnerability
🇺🇸 unknown
added 2026-07-14 · arXiv 2026-07-13
NeuralActuator: a neural model that predicts actuator dynamics, external forces, and motor conditions to improve sim-to-real transfer on low-cost robot platforms, with a new annotated dataset.
- Addresses practical sim-to-real gap by modeling nonlinear actuator effects (friction, hysteresis, backlash, thermal) that dominate on low-cost platforms; jointly optimizes multiple objectives (dynamics surrogate, sensorless force perception, condition monitoring)
- Demonstrates generalization across three actuator families and platforms ranging $500–$30k; introduces Neural Actuation Dataset with robot states, telemetry, and ground-truth force labels
- Differentiable training of torque surrogate via trajectory simulation without direct generalized-effort labels is technically novel; shows practical gains in behavior cloning and motor diagnostics
robot-learningsim-to-realneural-dynamicsopen-source-datasetefficiency
abstract
pdf
Zhiyang Dou, John U. Onyemelukwe, Hangxing Zhang, Heng Zhang, Minghao Guo et al.
🇺🇸 University of Michigan
added 2026-07-14 · arXiv 2026-07-13
Introduces MCLASH benchmark and MET, a theory-grounded prompting method with self-distillation for culturally-aware multilingual moral reasoning without external supervision.
- Addresses genuine gap in multilingual LLM evaluation: culture-specific moral reasoning rather than rote translation, with systematic variation across languages
- Novel inference + training pipeline combining psychology/philosophy-grounded scaffolding with self-distillation, avoiding expensive human annotation or model supervision
- Consistent gains across model families and sizes (Qwen, Gemma) with strong per-language improvements (12.94pt peak), plus measurable shift toward native-language reasoning
multilingualmoral-reasoningbenchmarkspromptingdistillation
abstract
pdf
Ayoung Lee, Ryan Kwon, Yunxiang Zhang, Yuxuan Liu, Peter Railton et al.
National Taiwan University
added 2026-07-14 · arXiv 2026-07-13
IAAN identifies and amplifies specific neurons in audio encoders at inference time to improve fine-grained acoustic perception in large audio-language models without retraining.
- Novel neuron-level intervention in the audio encoder (not post-encoder) using activation contrasting with noise references—a genuinely unexplored direction for inference-time acoustic steering
- Strong empirical gains (25.7pts on Audio-Flamingo, 21.4pts on Qwen2.5-Omni) with training-free, label-free methodology that proves specific neuron identity matters, not just count
- Reveals encoder-side bottleneck in LALMs for non-semantic speech attributes; cleanly ablated evidence that decoder/LM-side interventions fail, establishing where the acoustic signal is lost
inference-timemultimodalaudioneuron-steeringefficiency
abstract
pdf
Yu-Han Huang, Chih-Kai Yang, Ke-Han Lu, An-Yu Cheng, Hung-yi Lee
🇺🇸 Apple
added 2026-07-14 · arXiv 2026-07-13
Unified benchmark for evaluating multimodal tool-calling agents with 500+ tools across 16 domains, revealing that visual precision (not planning) is the key bottleneck even for frontier models.
- Stateful execution environment with 258 verified scenarios + automated generation pipeline addresses real gap in agent evaluation: current benchmarks don't test grounded multi-turn tool use with realistic visual/conversational phenomena
- Comprehensive analysis across 12 SOTA models (4B to frontier) identifies planning-to-precision capability crossover by scale, actionable for research prioritization
- Open benchmark and framework (500+ tools, 16 domains) will enable systematic study of visual grounding failures in agentic systems
agentsmultimodaltool-useevaluationbenchmark
abstract
pdf
Kaixin Ma, Di Feng, Alexander Metz, Jiarui Lu, Eshan Verma et al.
🇺🇸 unknown
added 2026-07-14 · arXiv 2026-07-13
A benchmark suite for evaluating advanced mathematical proof generation and verification in LLMs, with expert-annotated automatic verification pipeline and fine-grained error assessment.
- Addresses genuine gap in LLM evaluation: advanced mathematics beyond olympiad-level with rigorous proof verification, not just final-answer checking
- Introduces scalable automatic verification pipeline trained on expert annotations, enabling granular error detection beyond binary correctness
- Reveals concrete limitations of frontier models (GPT-4o, etc.) on proof construction and verification, highlighting critical bottleneck in error detection capability
reasoningbenchmarkverificationmathematical-reasoningevaluation
abstract
pdf
Lingkai Kong, Zijian Wu, Yuzhe Gu, Haiteng Zhao, Wenyong Huang et al.
🇺🇸 Anthropic
added 2026-07-13 · arXiv 2026-07-10
Systematic study showing additive activation steering has unpredictable and sometimes dangerous transfer properties from chat to agentic (ReAct) deployments, with refusal bypasses amplifying up to 2x on some models.
- First rigorous chat-to-agent transfer analysis of steering with matched-information design and representation read-outs, revealing dissociation between directional strength and behavioral coupling
- Identifies additive-specific mechanism via directional ablation and localizes rescaling to ReAct format scaffold, establishing mechanistic understanding rather than just empirical observation
- Direct safety implication: steering-based jailbreaks are unpredictably amplified in agentic deployment (up to 2x on Gemma-2-9B), creating a critical gap between safety analysis and real-world deployment
steeringsafetyagentsmechanistic-interpretationpost-training
🇺🇸 Google
added 2026-07-13 · arXiv 2026-07-10
GRACE: a graph-based system for reliably evolving LLM agent instructions over long horizons by structuring context as typed semantic graphs with local verification, improving telecom agent reliability from 9% to 67%.
- Novel structural approach to agentic context management: uses typed semantic graphs instead of flat-text instructions to enable local, scoped verification of proposed updates—addressing a real deployment challenge.
- Strong empirical gains on a controlled long-horizon evolution protocol (5 replications) with 7.4x improvement in pass@3 reliability versus zero-shot baseline, exceeding stronger Gemini 3.1 Pro reference.
- Identifies a genuine operational constraint: as instruction sets accumulate during agent evolution, verification becomes intractable without structural substrate; proposes consolidation mechanism to keep content usable.
agentspost-trainingreliabilitysystem-prompt
🇺🇸 unknown
added 2026-07-13 · arXiv 2026-07-10
Self-Guided Test-Time Training improves long-context LLM reasoning by selectively adapting only on relevant evidence spans, achieving 15% relative gains on LongBench.
- Test-time training (TTT) for long contexts is computationally expensive; S-TTT mitigates this by having the model self-identify relevant spans before adaptation, making TTT practical at scale.
- Addresses a fundamental failure mode: models struggle to locate and use evidence in long inputs; the self-guided selection mechanism is intuitive and empirically validates that span quality dominates TTT success.
- Demonstrates consistent improvements across diverse models (Qwen3-4B-Thinking, Llama-3.1-8B) and challenging benchmarks (LongBench-v2, LongBench-Pro), suggesting generality.
test-time-traininglong-contextpost-trainingreasoningefficiency
abstract
pdf
Xinyu Zhu, Zhe Xu, Xiaohan Wei, Yunchen Pu, Fei Tian et al.
🇩🇪 Deutsche Telekom (German Industrial AI Cloud)
added 2026-07-13 · arXiv 2026-07-10
Sovereign open-source 30B MoE-Transformer hybrid matching 14-27B dense models with superior code performance, trained entirely on German infrastructure with full transparency.
- Hybrid MoE-Mamba design activates only 3B/30B parameters per token with constant-size inference cache—material efficiency/throughput advantage for long-context deployment
- Strong multilingual foundation (German-English) with deliberate German up-weighting, outperforming larger European baselines and matching/exceeding Olmo 3 32B and Apertus 70B on open benchmarks
- Full transparency (weights, checkpoints, per-source accounting, training code) under highly permissive licenses—rare level of open governance for sovereign AI
moeefficiencyopen-weightsmultilingualsovereign
abstract
pdf
The Soofi-Team, :, Benedikt Droste, David Fitzek, Ruben Härle et al.
🇺🇸 unknown
added 2026-07-13 · arXiv 2026-07-10
Novel framework coupling explanations and predictions via an LLM agent that generates faithful explanation sets, improving both accuracy and interpretability on real-world classification/regression tasks.
- Reframes explainability-accuracy trade-off as coupling problem; theoretical guarantees on fidelity and set non-emptiness
- LLM-based agentic workflow (Explanation-Prediction-Reflection) with convergence proof that recovers explanation sets while improving accuracy
- Validated on large-scale live production tasks (churn, survival, CTR) showing practical wins over XAI baselines with robustness to distribution shift and temporal splits
interpretabilityllm-agentsxaipost-trainingreasoning
🇨🇳 Peking University
added 2026-07-13 · arXiv 2026-07-10
First systematic energy profiling of edge VLM inference revealing that decoding (output tokens), not vision processing, dominates energy cost—contradicting implicit assumptions in the field.
- Empirical energy profiling across 5 VLMs, 3 architectures, 2 platforms with surprising findings: inference power is model-intrinsic, output tokens cost 11-39x more than input tokens, visual pruning saves ≤10% energy
- Demonstrates fundamental asymmetry in prefill vs decode compute/memory bounds for VLMs at edge scale, with implications for efficiency research direction
- Quantifies image complexity effects (4.1x variation) arising from output length rather than visual processing—key insight for embodied AI systems on constrained hardware
efficiencyvlmedge-inferenceenergy-profilingpost-training
abstract
pdf
Junfei Zhan, Haoxun Shen, Mingang Guo, Zixuan Huang, Tengjiao He
unknown
added 2026-07-13 · arXiv 2026-07-10
PAC-ACT applies actor-critic RL post-training to action-chunking transformers for industrial contact manipulation, improving force control and stability while maintaining real-time performance.
- Action-chunking policies are underexplored for RL post-training; reformulating at chunk level rather than token level is a natural but non-trivial contribution for real-time control
- Hybrid behavior-prior constraint elegantly balances RL exploration with BC pretraining—addresses core tension in vision-action policy learning
- Demonstrates substantial gains on contact-rich industrial tasks (46× reduction in excessive force readings) under realistic pose perturbations and sparse rewards
rlroboticspost-trainingefficiency
🇨🇳 Infinity AI
added 2026-07-10 · arXiv 2026-07-08
Large multimodal document parser with 5M synthetic bilingual corpus and multi-task RL achieving SOTA on OCR and parsing benchmarks.
- 5M synthetically-generated bilingual document corpus (Infinity-Doc2-5M) with rich annotations (bboxes, markdown/HTML/LaTeX, reading order) addresses real scarcity of faithfully labeled parsing data
- Multi-task joint RL across 8 co-trained objectives (parsing, layout, tables, math/chemical formulas, charts, VQA) unifies perception and reasoning in single optimization signal—novel training approach
- Open-source model variants (Flash for latency, Pro for precision) with SOTA results (87.6% olmOCR, 74.3% ParseBench) and strong generalization across diverse document types
document-parsingmultimodalsynthetic-datareinforcement-learningopen-weightsocr
abstract
pdf
Zuming Huang, Jun Huang, Kexuan Ren, Baode Wang, Weizhen Li et al.
🇩🇪 unknown
added 2026-07-10 · arXiv 2026-07-08
Explains the origin of near-zero Hessian eigenvalues in neural networks as weakly broken continuous symmetries, with explicit constructions and spectral analysis.
- Provides mechanistic explanation for a widespread phenomenon (near-zero modes dominating loss landscape) through symmetry breaking—moves beyond empirical observation to theory
- Constructs exact zero modes in deep linear networks analytically and traces how ReLU nonlinearity weakly breaks them, generalizing to convolutional architectures
- Directly relevant to optimization and loss landscape geometry, with implications for understanding training dynamics and generalization
loss-landscapehessiansymmetrytheoryoptimization
🇺🇸 unknown
added 2026-07-10 · arXiv 2026-07-08
Multi-agent LLM workflow for automated formalization of tensor network theory in Lean, with new libraries and proof discovery.
- First demonstration of LLM-agent team autonomously formalizing research-level physics (matrix-product states theorem) with novel proof routes
- Produces TNLean library extending Mathlib with tensor network and quantum information primitives previously unavailable
- Systematic study of bottlenecks in large-scale autoformalization, emphasizing mathematical intent enforcement as key challenge
agentsformalizationreasoningquantumlibraries
unknown
added 2026-07-10 · arXiv 2026-07-08
Comprehensive empirical study comparing softmax and four linear-attention mechanisms (DeltaNet, Gated DeltaNet, Kimi Delta, etc.) at 350M–3B scale, introducing cross-layer routing for improved long-context efficiency.
- Systematic comparison of competing linear-attention schemes with explicit recurrent-memory formalism, revealing trade-offs in expressivity, throughput, and loss—rare engineering-level analysis for practitioners
- Novel cross-layer routing (CLVR) mechanism for linear-attention stacks shows consistent improvements, suggesting architectural refinements beyond individual layer design
- Large-scale training sweeps (15B tokens, up to 3B params) with multiple optimizers (AdamW, Muon) provide empirical grounding often missing in architectural papers
linear-attentionefficiencylong-contextarchitecturepost-training
abstract
pdf
Tommaso Cerruti, Tim Rieder, George Rowlands, Lingfeng Jin, Imanol Schlag
🇺🇸 Yale University
added 2026-07-10 · arXiv 2026-07-08
KronQ improves post-training quantization of LLMs by incorporating gradient covariance via Kronecker-factored Hessian, achieving extreme 2-bit quantization where existing methods fail.
- Addresses critical limitation of GPTQ by jointly modeling activation and gradient covariances in quantization objective, not just input statistics
- Achieves dramatic empirical breakthrough: 2-bit quantization on LLaMA-70B (7.93 perplexity vs. >2000 for GPTQ/GPTAQ), enabling practical ultra-low-bit compression
- Novel bidirectional incoherence processing and Hessian-trace-based mixed-precision allocation provide principled mechanisms beyond existing PTQ art
quantizationpost-trainingcompressionefficiencyhessian
abstract
pdf
Donghyun Lee, Yuhang Li, Ruokai Yin, Priyadarshini Panda
🇺🇸 unknown
added 2026-07-10 · arXiv 2026-07-08
TACO improves LLM RL by calibrating credit assignment to suppress reinforcement of low-probability erroneous tokens, enabling more stable training and better generalization.
- Identifies a concrete failure mode in critic-free RL (Positive-Credit Contamination) where tail tokens get identical positive credit regardless of contextual plausibility, then proposes a principled tail-risk scoring mechanism to suppress undesirable updates
- Demonstrates consistent improvements over GRPO-style baselines across three LLMs and eight benchmarks with explicit focus on training stability and long-horizon RL
- Practical method that preserves gradients for useful rare patterns while dampening noise, addressing a gap between uniform and fully selective credit assignment
rlpost-trainingreasoningcredit-assignment
abstract
pdf
Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang, Hoang Anh Duy Le, Zhaozhuo Xu et al.
🇺🇸 University of Washington
added 2026-07-10 · arXiv 2026-07-09
PLURAL is a 500k preference dataset grounded in 92-country survey data for culturally-aligned value steering in LLMs, validated across 20 countries with human eval.
- Addresses a real gap: most preference datasets and alignment approaches reflect Western values; PLURAL systematically captures diverse cultural value systems at scale
- Rigorous methodology: builds on Integrated Values Survey (nationally representative), synthetic generation pipeline preserves normative signals, multi-stage validation (dataset-level, automated, blind human evals with 176 evaluators)
- Practical impact: shows 27.7% relative error reduction in cultural alignment; released dataset enables reproducible research on pluralistic alignment
alignmentdatasetscultural-diversityvaluespreference-learning
abstract
pdf
Dhruv Agarwal, Anya Shukla, Tanya Goyal, Aditya Vashistha
🇺🇸 unknown
added 2026-07-10 · arXiv 2026-07-09
Probes of LLM internal representations reveal that forecasting models' CoT reasoning is often unfaithful, while activation-based lie detectors outperform explicit reasoning traces for calibration and behavioral auditing.
- Demonstrates that CoT reasoning traces fail to faithfully reflect actual drivers of model predictions through evidence ablation/injection experiments, suggesting post-hoc rationalization.
- Shows representation-pooling probes achieve substantially better calibration than explicit model outputs, and can predict behavioral shifts in 84% of cases even when CoT obscures them.
- Reveals forecasts are largely predetermined before reasoning generation (fixed by single pre-reasoning pass), enabling token-efficient routing with 30-47% token savings—practical for deployment.
interpretabilitycalibrationpost-trainingreasoningprobing
abstract
pdf
Raphaël Sarfati, Pratyush Ranjan Tiwari, Siddharth Boppana, Christopher J. Earls, Srikar Varadaraj et al.
🇺🇸 unknown
added 2026-07-10 · arXiv 2026-07-09
Large-scale empirical study showing agreement among LLMs or within a model's samples is a weak and unreliable confidence signal, with frontier models exhibiting overconfident yet incorrect consensus.
- Challenges a widespread assumption in LLM evaluation pipelines (LLM-as-judge, ensemble judges); shows agreement ≠ accuracy with real deployment consequences
- Rigorous cross-model, cross-runner analysis (265K samples across GPQA/AIME) with careful statistical methods (hierarchical bootstrap, item-clustering); regime-dependent findings (agreement fails worst for frontier models)
- Public release of per-run distributions enables reproducible evaluation methodology research; directly relevant to production monitoring and confidence calibration
evaluationllm-as-judgeconfidence-calibrationbenchmarkingbias
🇺🇸 Anthropic
added 2026-07-10 · arXiv 2026-07-09
Reveals that chain-of-thought monitoring can be exploited via persuasion attacks, and proposes model-diverse fact-checking as a mitigation.
- Identifies a concrete vulnerability in CoT safety mechanisms—a widely-assumed alignment technique—showing CoT reasoning *increases* harmful approval by 9.5% when agents argue persuasively
- Proposes and validates a practical defense (model-diverse fact-checking pairs reducing harmful approval by 45%), grounded in empirical eval across 40 tasks and thousands of interactions
- Directly relevant to agent oversight and safety monitoring, concerns shared by industry deployment
safetyalignmentmonitoringadversarialagents
abstract
pdf
Jennifer Za, Julija Bainiaksina, Nikita Ostrovsky, Tanush Chopra, Victoria Krakovna
🇺🇸 unknown
added 2026-07-10 · arXiv 2026-07-09
Systematic study of layer-patching strategies for zero-shot model size interpolation via boomerang distillation, with graph-theoretic optimization and practical greedy algorithms.
- Formulates layer selection for model interpolation as shortest-path optimization—provides theoretical grounding for a practical post-training technique.
- Introduces KLPatch, a principled greedy algorithm that improves over heuristic baselines and scales across model families.
- First systematic ablation of patching direction and strategy effects, revealing that simple sequential approaches are surprisingly effective—useful guidance for practitioners.
distillationmodel-compressioninterpolationpost-trainingefficiency
abstract
pdf
Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak, Marco Fumero, Francesco Locatello et al.
🇨🇳 unknown
added 2026-07-10 · arXiv 2026-07-09
LEEVLA introduces drift-guided dynamic prioritization and structured feature flow generation to improve vision-language-action models for robot control by learning what visual regions matter.
- Novel attention mechanism (DGDP) combining semantic drift guidance with dynamic prioritization to identify task-critical visual evidence
- Structured latent space reasoning via prototype-to-periphery prediction + topological consistency loss, improving interpretability of latent world models
- Consistent benchmark improvements on VLA tasks through principled 'where-how' training framework that avoids treating all visual tokens uniformly
vision-language-actionmultimodalroboticsattentionlatent-space
abstract
pdf
Qi Lyu, Baicheng Liu, Xudong Wang, Jiahua Dong, Lianqing Liu et al.
🇺🇸 unknown
added 2026-07-10 · arXiv 2026-07-09
Multi-teacher knowledge distillation framework using execution-based verification and RL with verifiable rewards to improve code LLMs, showing RL beats imitation on harder problems.
- Execution-based judge (unit tests) rather than LLM judge avoids bias; reveals saturation on standard benchmarks but separation on harder problems
- Key finding: SFT on verified solutions degrades student performance; RLVR (RL with verifiable rewards) reverses this, +49% relative gain on competition problems
- Reproducible on-prem pipeline released for running GRPO with verification environment—practical contribution for training pipeline design
knowledge-distillationrlpost-trainingcode-generationverification