AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsCP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation Workflows
arXiv:2609.31790v1 Announce Type: new Abstract: Crystal plasticity (CP) simulations predict the mechanical behavior of polycrystalline metals, yet their routine use is hindered by the manual effort of configuring heterog…
- arXiv cs.AIresearchConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts
arXiv:2609.31792v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models perform strongly on manipulation tasks, their responses to invalid task premises remain underexplored. Existing evaluations of pre…
- arXiv cs.AIresearchWorking with AI: A Design Framework for Human-AI Collaboration
arXiv:2609.31793v1 Announce Type: new Abstract: Artificial Intelligence (AI), particularly GenAI, is becoming an increasingly important part of modern work. In industrial settings, AI can support decision-making, automat…
- arXiv cs.AIagentsDriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution
arXiv:2609.31814v1 Announce Type: new Abstract: Evaluating VLM-based autonomous driving remains difficult because driving competence is composite, where a capable system must ground traffic participants and hazards, inte…
- arXiv cs.AIresearchLLM Judge Validation Under Sparse Overlap: From Inference to Design
arXiv:2609.31857v2 Announce Type: replace Abstract: Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. We prove that this ov…
- arXiv cs.AIresearchMetro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals
arXiv:2609.31868v3 Announce Type: replace Abstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effective over short pl…
- arXiv cs.AIresearchIndustryLLM: Failure-Driven LLM Training for Industrial Procurement
arXiv:2609.31871v1 Announce Type: new Abstract: Industrial procurement requires language models to bridge informal buyer jargon, sparse marketplace attributes, and authoritative engineering standards under strict safety…
- arXiv cs.AIagentsCOUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents
arXiv:2609.31874v1 Announce Type: new Abstract: Existing agent memory frameworks mainly create memory through an agent's interaction with the factual world, e.g., remembering feedback from actions taken to improve perfor…
- arXiv cs.AIagentsContext-dependent agent evaluation with orthogonal equilibrium learning
arXiv:2609.31897v1 Announce Type: new Abstract: Many applications require to evaluate agents under contextual information (e.g., a prompt, task, or user group). We study how to perform such context-dependent agent evalua…
- arXiv cs.AIagentsChoir: An Open Protocol for Distributed Multi-Agent Autoformalization
arXiv:2609.31903v1 Announce Type: new Abstract: AI agents can now formalize entire textbooks and major theorems in proof assistants such as Lean, but current efforts are typically centralized: a single team runs all agen…
- arXiv cs.AIagentsEmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity Tasks
arXiv:2609.31906v1 Announce Type: new Abstract: Enterprise email agents must combine information retrieval, structured state changes, temporal reasoning, and multi-step coordination. Recent agent benchmarks include produ…
- arXiv cs.AIresearchImproving Medical Calculation of LLMs with Embedded Coding
arXiv:2609.31908v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on medical examinations and question-answering benchmarks, but remain unreliable on medical calculation tasks that require exact n…
- arXiv cs.AIagentsBioDyad: Synchronize Biomedical Discovery and Machine Learning Engineering
arXiv:2609.31939v1 Announce Type: new Abstract: Agentic biomedical machine learning (ML) draws on complementary advances in biomedical evidence acquisition and executable program search. Existing systems connect aspects…
- arXiv cs.AIagentsSymbolic Guidance for LLM Agents in Distributed Multiagent Coordination
arXiv:2609.31963v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in multi-agent systems, yet their ability to reliably execute distributed coordination proto…
- arXiv cs.AIagentsGoal-Persistent Coding Agents as Scientific Performance Engineers: A Fixed-Radius Nearest-Neighbor Case Study
arXiv:2609.31980v1 Announce Type: new Abstract: Coding agents can pursue persistent objectives across many tool-use turns, but evidence that general-purpose agents can conduct rigorous scientific performance engineering…
- arXiv cs.AIagentsCSI-Agent: LLM-Assisted Few-Shot Adaptation for Cross-Domain Wi-Fi CSI Sensing
arXiv:2609.31990v1 Announce Type: new Abstract: Wi-Fi channel state information (CSI) has enabled device-free sensing applications such as human activity recognition. However, CSI sensing models remain brittle in cross-d…
- arXiv cs.AIagentsSenseAgent: An LLM Agent for Adaptive Cross-Domain IMU Sensing
arXiv:2609.32000v1 Announce Type: new Abstract: Deep learning has improved inertial measurement unit (IMU) sensing for mobile and wearable applications. However, an IMU model trained in one domain often becomes unreliabl…
- arXiv cs.AIresearchWhat Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation
arXiv:2609.32002v2 Announce Type: replace Abstract: The rank $r$ in LoRA is widely treated as a capacity control: a smaller rank is assumed to yield a simpler model that generalizes better. We show that, under hard per-f…
- arXiv cs.AIagentsDecentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding
arXiv:2609.32019v1 Announce Type: new Abstract: Decentralized multi-agent path finding (MAPF) with communication requires agents to reach individual goals without collisions under partial observability. Learnable policie…
- arXiv cs.AIresearchA Benchmark for LLM's Understanding of Middle School and High School Science Topics
arXiv:2609.32020v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into educational settings, yet educators lack robust, standards-aligned tools to evaluate their effectiveness in K-…
- arXiv cs.AIresearchReasoning Concentrates Errors, and Self-Consistency Never Notices
arXiv:2609.32035v1 Announce Type: new Abstract: Self-consistency assumes that independent samples disagree when a model is unsure, so agreement is evidence of correctness. Holding weights fixed and toggling only a reason…
- arXiv cs.AIagentsReceiver-Conditioned Latent Communication gives 94% CacheBack
arXiv:2609.32046v1 Announce Type: new Abstract: Multi-agent systems distribute large contexts across agents that communicate to solve a task. Text messages are compact but require decoding and may omit evidence the recei…
- arXiv cs.AIagentsEngramRAG: Dynamic Usage-Weighted Topology and Synaptic Consolidation for Multi-Hop Agentic Memory
arXiv:2609.32049v1 Announce Type: new Abstract: As autonomous LLM agents are deployed across multi-session environments, conventional memory architectures suffer from Associative Blindness (inability to traverse multi-ho…
- arXiv cs.AIagentsContract monitoring: governing AI via separation of powers
arXiv:2609.32061v1 Announce Type: new Abstract: We propose an AI safety framework that binds worker agents to contracts specifying their permitted actions. We show how these contracts can be enforced and specified by ass…
- arXiv cs.AIagentsToward Interactive Understanding of Code APIs
arXiv:2609.32081v1 Announce Type: new Abstract: Empowered by advances in Language Model agents, systems have made substantial strides in code generation and understanding. However, these approaches often rely on read acc…
- arXiv cs.AIagentsMemory as Middleware for Self-Improving AI Agents
arXiv:2609.32091v1 Announce Type: new Abstract: AI agents are stateless across sessions by default and therefore operationally amnesic: each session begins with little durable knowledge of prior failures, repairs, prefer…
- arXiv cs.AIagentsGameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games
arXiv:2609.32093v1 Announce Type: new Abstract: Powered by expert guidance, agents can operate in interactive environments; however, it is unclear whether they can learn autonomously from their own experience. To evaluat…
- arXiv cs.AIresearchResidual Streams Read, Recurrent States Remember: The Global Workspace in Mamba Models
arXiv:2609.32102v1 Announce Type: new Abstract: Can the global-workspace account of transformer representations extend to state-space language models? We fit Jacobian lenses to the residual streams and recurrent states o…
- arXiv cs.AIresearchEscaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking
arXiv:2609.32116v1 Announce Type: new Abstract: Best-of-$N$ jailbreaking (BoN) bypasses safeguards of aligned models by drawing $N$ independent augmentations of an unsafe prompt and sampling $M$ completions of each. Prev…
- arXiv cs.AIresearchREAD-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis
arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through downstream predicti…
- arXiv cs.AIagentsPastForward: Faster On-Device GUI Agents via Computational Experience Reuse
arXiv:2609.32166v1 Announce Type: new Abstract: Running GUI agents on edge devices can keep sensitive screens and interaction histories local, but the computational cost of inference at every action step makes deployment…
- arXiv cs.AIresearchNoisy Test-Time Reinforcement Learning for Code LLMs
arXiv:2609.32172v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance across various code-related tasks. However, unlike carefully curated datasets that are typically high-…
- arXiv cs.AIagentsAI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents
arXiv:2609.32184v1 Announce Type: new Abstract: Foundation-model agents are often modeled as policies over an observed state. In deployed systems, however, a runtime may intervene only after the model has emitted a seman…
- arXiv cs.AIagentsCoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies
arXiv:2609.32192v2 Announce Type: replace Abstract: Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information must remain isolate…
- arXiv cs.AIresearchInstruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation
arXiv:2609.32201v2 Announce Type: replace Abstract: On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the tea…
- arXiv cs.AIagentsWitness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments
arXiv:2609.32208v1 Announce Type: new Abstract: Automated science needs agents that can work out the rules of an unfamiliar environment by interacting with it. Interactive rule-discovery puzzles offer a controlled settin…
- arXiv cs.AIresearchFracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
arXiv:2609.32209v1 Announce Type: new Abstract: Time series foundation models must preserve multi-domain breadth, probabilistic output, and multiple temporal scales, but parameter count grows when each scale receives a s…
- arXiv cs.AIresearchA bilingual AI audiologist built through rubric-guided closed-loop engineering outperforms human audiologists in a blinded evaluation of simulated cases
arXiv:2609.32220v2 Announce Type: replace Abstract: Audiology consultation requires structured history-taking, audiometric interpretation and patient-centred communication, yet real-world case material is scarce. We pres…
- arXiv cs.AIresearchRAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation
arXiv:2609.32224v1 Announce Type: new Abstract: We explore whether Omni-Language Models (OLMs) can be directly applied to zero-shot Semantic Audio-Visual Navigation (SAVN). Recent work demonstrates that even state-of-the…
- arXiv cs.AIresearchCertifying Interventional Agreement Among Observationally Equivalent Causal Models
arXiv:2609.32247v1 Announce Type: new Abstract: Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occur in observational dat…
- arXiv cs.AIresearchWhy Directly Learning Periodic Trajectories Can Fail
arXiv:2609.32254v1 Announce Type: new Abstract: Operator learning of periodic solutions requires deciding how simulation data should be recorded and represented. A natural choice is to integrate long enough for transient…
- arXiv cs.AIagentsClarify the User or Verify the World? Uncertainty Routing for Proactive Agents
arXiv:2609.32255v1 Announce Type: new Abstract: Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proactive approaches often…
- arXiv cs.AIagentsLAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound
arXiv:2609.32256v1 Announce Type: new Abstract: Agent memory grows as agents read inputs, reason, and call tools. Longer histories increase inference cost and eventually exceed the context window. LLM-based summarization…
- arXiv cs.AIagentsPrefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
arXiv:2609.32259v2 Announce Type: replace Abstract: Recent multi-agent LLM systems increasingly combine heterogeneous models for specialized agent roles. However, text-based communication requires each receiver to prefil…
- arXiv cs.AIagentsWhen Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use
arXiv:2609.32274v1 Announce Type: new Abstract: Agent skills are expected to improve task performance. Yet we find that they often provide no benefit, and can even hurt performance while incurring additional token costs.…
- arXiv cs.AIagentsGLIDE: Generalized Layer-wise Intrinsic Distributional Evaluation for Heterogeneous LLM Agents
arXiv:2609.32295v1 Announce Type: new Abstract: LLM agents require reliable step-level evaluation to compare candidate branches and allocate computation effectively. However, lightweight evaluation remains challenging. E…
- arXiv cs.AIagentsAgentsensus: Consensus-Compressed Shared Memory for Multi-Agent Story Worlds
arXiv:2609.32297v1 Announce Type: new Abstract: A agentic story world is a dynamic system simulating who learned what, when, and from whom -- yet the standard design gives each character a private memory stream. A shared…
- arXiv cs.AIresearchTrain4Merge: RL or SFT---Which Yields Better Teachers for OPD-Based Model Merging?
arXiv:2609.32303v3 Announce Type: replace Abstract: Domain experts trained from a shared checkpoint can transfer their specialized capabilities to a single student through on-policy distillation (OPD). Existing research…
- arXiv cs.AIresearchPhiFold: Towards Dynamic Protein Design with Physics-Structured Covariance Modeling
arXiv:2609.32309v1 Announce Type: new Abstract: Protein design is moving beyond structural correctness toward function-aware design, yet existing generative models typically treat dynamics as a downstream property estima…
- arXiv cs.AIresearchDelayed Supervision for Test-Time Language Models
arXiv:2609.32312v1 Announce Type: new Abstract: Test-time language models adapt a compact memory while processing the input sequence. This perspective encompasses nonlinear fast-weight learning in LaCT, associative delta…