AI news archive.
19,871 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsFyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization
arXiv:2609.39228v1 Announce Type: new Abstract: We present FYAN, a human--AI harness for document-level mathematical formalization. Rather than treating theorems in isolation, FYAN coordinates an end-to-end workflow span…
- arXiv cs.AIresearchEffective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
arXiv:2609.39259v1 Announce Type: new Abstract: Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by component importance…
- arXiv cs.AIresearchANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning
arXiv:2609.39294v1 Announce Type: new Abstract: Precise numerical reasoning with Large Language Models (LLMs) is essential for expanding their applicability to complex real-world tasks. However, text-based tokenization o…
- arXiv cs.AIagentsMiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate
arXiv:2609.39297v1 Announce Type: new Abstract: Autonomous agents powered by large language models (LLMs) are rapidly evolving into an open agentic ecosystem. To support trustworthy collaboration, industry initiatives in…
- arXiv cs.AIagentsWorkGenesis: Building the Worlds That Teach Agents to Work
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents requires realistic work sce…
- arXiv cs.AIresearchUnderstanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Models
arXiv:2609.39341v1 Announce Type: new Abstract: Does a language model merely predict tokens, or does it understand what it says? We make this question measurable by defining "understanding" through the lens of no-arbitra…
- arXiv cs.AIresearchThe Golden Path Hypothesis: Reusable Schedules in Diffusion Caching
arXiv:2609.39343v1 Announce Type: new Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introduce the Golden Path Hy…
- arXiv cs.AIresearchOn the Complexity of Preference-Based Bandits
arXiv:2609.39351v1 Announce Type: new Abstract: We study preference-based bandits with general reward function classes, where a learner sequentially selects pairs of arms and observes binary preference feedback governed…
- arXiv cs.AIresearchAutoresearch in Mixed-Integer Linear and Nonlinear Programming
arXiv:2609.39360v2 Announce Type: replace Abstract: Despite recent progress in autoresearch, applying it to practical operations research problems, typically formulated as NP-hard mixed-integer linear or nonlinear progra…
- arXiv cs.AIagentsEHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning
arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical…
- arXiv cs.AIagentsSkillFM: Generating Skills for LLM Agents via Latent Flow Matching
arXiv:2609.39382v1 Announce Type: new Abstract: Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with…
- arXiv cs.AIagentsExperimental Experience Modeling for Autonomous Research
arXiv:2609.39392v1 Announce Type: new Abstract: Autonomous research agents can generate hypotheses and conduct experiments, but experimentation remains a major source of computational cost. A fundamental challenge is dec…
- arXiv cs.AIresearchCan Computation from Earlier Problems Help LLMs Solve New Ones?
arXiv:2609.39394v1 Announce Type: new Abstract: Large language models often solve independent problems in the same conversation. Can computation from earlier problems help them solve new ones? To answer this question, we…
- arXiv cs.AIresearchAdvancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization
arXiv:2609.39402v2 Announce Type: replace Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent methods use token ent…
- arXiv cs.AIresearchInferring Causal Relations between Two Sequences of Events with Language Models
arXiv:2609.39406v1 Announce Type: new Abstract: Causal AI is a branch of Artificial Intelligence which helps understand and reason about cause and effect relationships, not just patterns or correlations. Causal discovery…
- arXiv cs.AIagentsBeyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
arXiv:2609.39473v1 Announce Type: new Abstract: Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and believed, and leverag…
- arXiv cs.AIresearchWho Owns That? Evaluating Ownership Intuitions in Large Language Models
arXiv:2609.39483v1 Announce Type: new Abstract: Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appropriately with people…
- arXiv cs.AIresearchDisentangling Self-Distillation: Measuring and Modeling Acquisition and Retention
arXiv:2609.39494v1 Announce Type: new Abstract: Self-distillation with privileged context adapts a language model from demonstrations by letting the model, once conditioned on a reference response, teach its context-free…
- arXiv cs.AIresearchReferential Uncertainty in Human--AI Collaboration
arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, similar referents com…
- arXiv cs.AIagentsGrowing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean
arXiv:2609.39544v3 Announce Type: replace Abstract: Recent achievements in AI-assisted mathematics require intensive interaction of agents with proof assistants to generate machine-checked proof certificates. Agents inte…
- arXiv cs.AIagentsRankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models
arXiv:2609.39551v1 Announce Type: new Abstract: Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experimental loop. Over lon…
- arXiv cs.AIagentsDivide and Collapse: MAPF-Collapse via Exact Decomposition into Independent Sub-Instances
arXiv:2609.39559v1 Announce Type: new Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produced by a modern MAPF…
- arXiv cs.AIagentsA2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?
arXiv:2609.39564v1 Announce Type: new Abstract: Delegating complete application development to coding agents requires preserving the intended design rather than simply producing plausible outputs through naive prompting.…
- arXiv cs.AIagentsAVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language Navigation
arXiv:2609.39579v1 Announce Type: new Abstract: Deploying vision-and-language navigation (VLN) agents in unseen environments remains challenging because unfamiliar layouts and visual conditions can cause execution to go…
- arXiv cs.AIresearchWhy Do Conventional World Models Fail to Learn Cellular Automata?
arXiv:2609.39604v1 Announce Type: new Abstract: Although conventional world models - auto-regressive or diffusion models based on transformers or convolutional networks - may learn surface statistics of world dynamics, c…
- arXiv cs.AIagentsChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning
arXiv:2609.39665v2 Announce Type: replace Abstract: Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This requires connecti…
- arXiv cs.AIresearchValues as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
arXiv:2609.39701v1 Announce Type: new Abstract: Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventional activation edits o…
- arXiv cs.AIresearchA helps B while B hurts A: directed transfer in instruction-tuning mixture
arXiv:2609.39702v1 Announce Type: new Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choice costs a fine-tuning…
- arXiv cs.AIresearchArchitectureIQ: On the Measure of Training Intuition
arXiv:2609.39714v1 Announce Type: new Abstract: Top researchers have good intuition, but do language models have as good intuition about model training as top AI researchers? To measure model intuition of LLMs and humans…
- arXiv cs.AIagentsTrust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents
arXiv:2609.39717v2 Announce Type: replace Abstract: Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority during a consequ…
- arXiv cs.AIagentsOverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation
arXiv:2609.39727v1 Announce Type: new Abstract: Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map…
- arXiv cs.AIagentsSafety of Latent Communication in Multi-Agent Systems
arXiv:2609.39788v3 Announce Type: replace Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhea…
- arXiv cs.AIresearchLearning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
arXiv:2609.39838v1 Announce Type: new Abstract: Chain-of-thought monitoring as an approach for AI oversight and control is threatened by the possibility of steganographic reasoning, where LLMs conceal their reasoning ins…
- arXiv cs.AIresearchFIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
arXiv:2609.39863v1 Announce Type: new Abstract: Large language models frequently fail to balance staying truthful with being supportive. They often exhibit sycophancy in responses to users, agreeing with false claims, of…
- arXiv cs.AIresearchCompletion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus Holding
arXiv:2609.39868v2 Announce Type: replace Abstract: Exploratory reinforcement learning (RL) on an operating bus fleet is impractical,while policies trained only from historical data cannot acquire new experience. Hybrid…
- arXiv cs.AIresearchGrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning
arXiv:2609.39869v1 Announce Type: new Abstract: Grammar-constrained generation guarantees syntactic validity, but can substantially degrade semantic quality when the model's preferred outputs are poorly aligned with the…
- arXiv cs.AIagentsOSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
arXiv:2609.39903v1 Announce Type: new Abstract: Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting special…
- arXiv cs.AIresearchConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible
arXiv:2609.39933v1 Announce Type: new Abstract: When designing machine learning models, desirable properties are often in tension: improving one behavior can impair another, so task progress can depend on alleviating the…
- arXiv cs.AIresearchCoverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis
arXiv:2609.39955v1 Announce Type: new Abstract: Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among several precursor se…
- arXiv cs.AIagentsBetter Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking
arXiv:2609.39958v1 Announce Type: new Abstract: Corporate and investment banking teams use presentations to support credit decisions and advise clients on financing and transactions. Producing these decks requires reconc…
- arXiv cs.AIagentsAIMS: An Agentic AI Framework for Sim-to-Real Multi-Modal ISAC
arXiv:2609.39964v2 Announce Type: replace Abstract: Multi-modal integrated sensing and communication (ISAC) enables environmental perception and reliable connectivity for intelligent wireless networks. Data-driven multi-…
- arXiv cs.AIagentsWhat Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents
arXiv:2609.39989v1 Announce Type: new Abstract: Background. A component replacement in a language-model agent changes an execution trajectory, potentially altering later observations, resource use, and recovery opportuni…
- arXiv cs.AIagentsWho Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents
arXiv:2609.40027v1 Announce Type: new Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and…
- arXiv cs.AIresearchPTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport Problems
arXiv:2609.40090v2 Announce Type: replace Abstract: Particle transport under multiple scattering is central to radiative transfer and plasma physics, yet high-fidelity Monte Carlo (MC) simulations must trace prohibitivel…
- arXiv cs.AIagentsAgent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
arXiv:2609.40111v2 Announce Type: replace Abstract: An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and the environment's…
- arXiv cs.AIresearchUnlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR
arXiv:2609.40115v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an important approach for improving reasoning during post-training. Recent work suggests that some difficul…
- arXiv cs.AIagentsLearning from Research: Toward Lifelong Agent Harness Evolution
arXiv:2609.40169v1 Announce Type: new Abstract: Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness,…
- arXiv cs.AIagentsBelief-Aware Multi-Agent Path Finding under Map Uncertainty
arXiv:2609.40269v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static obstacles are known in…
- arXiv cs.AIagentsPivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
arXiv:2609.40285v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-…
- arXiv cs.AIagentsHow Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
arXiv:2609.40303v1 Announce Type: new Abstract: Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon…