AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMoSPR: Histology-to-Gene Expression Prediction with Morpho-Spatial Macrostates and Low-Rank Molecular Programs
arXiv:2609.34280v1 Announce Type: new Abstract: Predicting molecular profiles from histopathology remains challenging because whole-slide images contain spatially organized, heterogeneous tissue patterns, while gene expr…
- arXiv cs.AIagentsControlScope: Workflow Revision and Reliability in LLM Agents
arXiv:2609.34313v1 Announce Type: new Abstract: How much of a running workflow should a language model agent revise? ControlScope compares continuing generated code, editing the next tool call's data arguments, and repla…
- arXiv cs.AIresearchDynamical Parameters: An Interpretability Framework for Time-Series Foundation Models
arXiv:2609.34316v1 Announce Type: new Abstract: This work studies a central gap in interpreting time-series foundation models (TSFMs): a dynamical property may be accessible in a hidden state even when the forecast fails…
- arXiv cs.AIresearchTest-Time Scaling via Budgeted Multi-Attribute Verification
arXiv:2609.34322v2 Announce Type: replace Abstract: Verifying LLM-generated answers under a shared computational budget requires jointly deciding which candidates to inspect and which verification attributes to evaluate.…
- arXiv cs.AIresearchKnowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
arXiv:2609.34327v1 Announce Type: new Abstract: Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve…
- arXiv cs.AIagentsSAGE: Structured Strategic Reasoning for Efficient LLM Game Playing
arXiv:2609.34342v2 Announce Type: replace Abstract: A strong LLM strategic agent should reason prospectively over uncertain futures, adapt its strategy to opponents' behavioral tendencies, and continuously recalibrate it…
- arXiv cs.AIresearchFuzzy Distribution Modeling for Synthetic Tabular Data Generation with Causality Preservation
arXiv:2609.34349v1 Announce Type: new Abstract: Synthetic tabular data generation provides an effective alternative for the training of machine learning models when real-world data is limited or inaccessible. However, th…
- arXiv cs.AIagentsSemRD-V2X: Closure-Guided Communication with Bounded Inference for Cooperative Perception
arXiv:2609.34353v1 Announce Type: new Abstract: Vehicle-to-Everything (V2X) cooperative perception improves 3-D detection by sharing intermediate features, but dense remote features may repeat context that the ego agent…
- arXiv cs.AIresearchImproving Large Language Models for Code through Runtime Program-State Reasoning
arXiv:2609.34359v1 Announce Type: new Abstract: Large language models receive limited explicit training in reasoning about runtime program states. We study whether training models to reason about runtime program states i…
- arXiv cs.AIresearchCoeF-SFL: Preserving Collaborative Server-Client Learning with Enhanced Communication Efficiency
arXiv:2609.34360v1 Announce Type: new Abstract: Split Federated Learning (SFL) enables resource-constrained clients to participate in collaborative training, but vanilla SFL exchanges smashed data and gradients at every…
- arXiv cs.AIagentsPersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents
arXiv:2609.34372v1 Announce Type: new Abstract: The profile of a role-playing agent usually depends on the pre-defined personality in a system prompt, whereas its memory processing pipeline, including prioritisation of s…
- arXiv cs.AIagentsOrg-Agent: Beyond Personal Assistants Towards Organizational Agents
arXiv:2609.34392v1 Announce Type: new Abstract: Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions. We identify two comple…
- arXiv cs.AIagentsSkillFocus: Evolving Agent Skills via Capability Decomposition
arXiv:2609.34397v1 Announce Type: new Abstract: Agent skill evolution seeks to improve reusable procedural guidance for large language model (LLM) agents through iterative revision. Existing methods base each revision ma…
- arXiv cs.AIresearchMathematics for and by human cognition: A resource-rational search for bottlenecks in problem-solving
arXiv:2609.34410v1 Announce Type: new Abstract: Human cognitive constraints are generally viewed as limiting factors in problem-solving. We argue that these constraints can instead play a critical role in driving advance…
- arXiv cs.AIresearchOSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue
arXiv:2609.34418v1 Announce Type: new Abstract: Maintaining persona consistency across multi-turn dialogues remains a core challenge for role-playing language models. Off-policy distillation from external teachers incurs…
- arXiv cs.AIagentsBeyond End-to-End Black Box Mapping: An Intentional Agent Framework for Cognitive-driven Facial Reaction Generation
arXiv:2609.34419v1 Announce Type: new Abstract: Automatic human-like facial reaction generation (FRG) is essential for building intelligent systems that can engage in human-computer interaction (HCI). While diverse and c…
- arXiv cs.AIagentsSocial Circuits behind Multi-agent Echo Chambers
arXiv:2609.34444v1 Announce Type: new Abstract: Language-model agents exchange messages to combine evidence, but their communication can also create echo chambers that reinforce shared errors. However, overall task perfo…
- arXiv cs.AIresearchCORTEX: Learning to Share and Specialize in Dense Language Models
arXiv:2609.34449v1 Announce Type: new Abstract: Large language models are trained on heterogeneous data mixtures, where different knowledge domains require both shared knowledge and specialization. Existing modular appro…
- arXiv cs.AIagentsEscaping Local Views: Discovering Latent Concepts for Interpretable Multi-Agent Reinforcement Learning
arXiv:2609.34459v1 Announce Type: new Abstract: Efficient cooperation is challenging due to the usual partial observability of each agent in multi-agent reinforcement learning. Recurrent networks encode local interaction…
- arXiv cs.AIresearchWhen Does Structured Knowledge Help Neural Theorem Proving?
arXiv:2609.34460v1 Announce Type: new Abstract: Does structured mathematical knowledge help LLMs prove theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal libraries such as Mathlib en…
- arXiv cs.AIagentsPowerBench: A Benchmark for Agentic Retrieval and Reasoning in Power Systems
arXiv:2609.34492v1 Announce Type: new Abstract: Large language model (LLM) agents offer new opportunities for automated analysis in industry. However, rigorous evaluation of such agents-for example, within power system s…
- arXiv cs.AIresearchDoes Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks
arXiv:2609.34506v1 Announce Type: new Abstract: Human-model alignment is critical for trustworthy AI-assisted decision-making systems. Yet, most work evaluates model predictions against single ground-truth labels, overlo…
- arXiv cs.AIagentsCan AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets
arXiv:2609.34510v1 Announce Type: new Abstract: AI-based trading methods have rapidly evolved from machine learning and reinforcement learning to large language models (LLMs) and trading agents, yet their performance is…
- arXiv cs.AIresearchEOPSA: Efficient On-Policy Self-Distilled Safety Alignment
arXiv:2609.34519v2 Announce Type: replace Abstract: On-Policy Self-Distillation (OPSD) has emerged as a promising paradigm for safety alignment, delivering dense, token-level supervision by distilling from a teacher cond…
- arXiv cs.AIagentsPairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use
arXiv:2609.34526v1 Announce Type: new Abstract: Memory-augmented assistants use retrieved preferences to guide their responses. A small change in the situation can change whether a preference is appropriate while barely…
- arXiv cs.AIagentsThe Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions
arXiv:2609.34537v1 Announce Type: new Abstract: Large language model (LLM)-based scientific agents are increasingly used for scientific problem solving, yet their robustness to imperfections arising during multi-turn int…
- arXiv cs.AIresearchAPOLO: Automatic Prompt Optimization for Ontology Learning
arXiv:2609.34540v2 Announce Type: replace Abstract: Ontology Learning (OL) from text has advanced with the emergence of Large Language Models (LLMs), but it remains challenging due to the limited availability of annotate…
- arXiv cs.AIagentsRemember Before You're Asked: MemDream for Self-Probing Memory Evolution
arXiv:2609.34545v1 Announce Type: new Abstract: Memory is essential for enabling LLM-based agents to maintain coherent, personalized behavior over long-horizon interactions. However, existing memory systems share a funda…
- arXiv cs.AIagentsSGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning
arXiv:2609.34548v1 Announce Type: new Abstract: Recent advances in reasoning backbones have empowered large language model (LLM)agentstotackle complex, multi-step tasks. However, as reasoning horizons grow, inconsistent…
- arXiv cs.AIagentsSkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents
arXiv:2609.34557v1 Announce Type: new Abstract: Recent work incorporates reusable skills distilled from past interactions into multimodal agent training, providing procedural guidance for long-horizon planning and tool u…
- arXiv cs.AIagentsFlowState: Execution State as Memory for Long-Horizon LLM Agents
arXiv:2609.34565v2 Announce Type: replace Abstract: Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases context costs, while c…
- arXiv cs.AIresearchPersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations
arXiv:2609.34571v1 Announce Type: new Abstract: Controlling persona in large language models (LLMs) at inference time is important for role-playing, personalized dialogue, and social simulation. Recent methods extract pe…
- arXiv cs.AIresearchNudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence
arXiv:2609.34572v1 Announce Type: new Abstract: Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for this must answer three q…
- arXiv cs.AIresearchDiffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
arXiv:2609.34575v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) learns goal-directed policies from reward-free data, but in long-horizon tasks, goal-conditioned value functions…
- arXiv cs.AIresearchCalibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring
arXiv:2609.34577v2 Announce Type: replace Abstract: Informative Path Planning for scalar field reconstruction uses predictive uncertainty to direct sensing vehicles toward maximally informative locations. Gaussian Proces…
- arXiv cs.AIresearchSpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences
arXiv:2609.34582v2 Announce Type: replace Abstract: Human speech conveys rich perceptual information, such as emotion and speaker identity, yet most automatic speech quality judges reduce it to a single naturalness score…
- arXiv cs.AIresearchTULIP: Targeted LLM Unlearning at Layers Identified Per-input
arXiv:2609.34591v2 Announce Type: replace Abstract: Representation-level unlearning modifies the intermediate hidden states of LLMs. Although knowledge is distributed across layers, existing methods operate at a single f…
- arXiv cs.AIagentsAfter the Fix: Transfer of Corrected Agent Experience
arXiv:2609.34603v2 Announce Type: replace Abstract: Does repairing an episode make its experience a better memory for the next task? We transfer the same failed source before and after accepted repair to a fixed target,…
- arXiv cs.AIagentsLLMs for Executable Multi-Agent System Specification Generation
arXiv:2609.34619v1 Announce Type: new Abstract: MAS specifications express the effects of the actions of the agents and their environment, as well as other temporal phenomena, such as the intervals during which an agent…
- arXiv cs.AIresearchA Persistent State for Auditable Mixture-of-Experts Routing
arXiv:2609.34634v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models repeatedly route tokens to sparse subsets of experts, but conventional routers expose no routing-specific record of how cross-layer influenc…
- arXiv cs.AIresearchMechReasoner: A Simulator and Benchmark for Mechanistic Reasoning in Qualitative Physics
arXiv:2609.34636v1 Announce Type: new Abstract: This work introduces MechReasoner, a mechanistic qualitative simulator grounded in confluence-based qualitative physics, together with a benchmark for mechanistic inference…
- arXiv cs.AIagentsBeyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses
arXiv:2609.34649v1 Announce Type: new Abstract: Harness evolution improves LLM agents by learning from execution trajectories, but existing experience- and skill-based methods are less effective on long-horizon tasks. As…
- arXiv cs.AIresearchOmniTide: Co-Designing Algorithms and Systems for Efficient On-Device Omni-LLM Streaming
arXiv:2609.34653v2 Announce Type: replace Abstract: On-device streaming omni-modal inference safeguards user privacy and eliminates prohibitive per-token API costs, but faces a critical bottleneck: the continuous influx…
- arXiv cs.AIresearchA General Harness for Protein Foundation Model Fitness Prediction
arXiv:2609.34654v1 Announce Type: new Abstract: Accurate fitness prediction is central to protein engineering and understanding sequence-function relationships. With advances in deep learning, protein foundation models (…
- arXiv cs.AIagentsJailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool Agents
arXiv:2609.34686v1 Announce Type: new Abstract: As large language models increasingly operate as tool-using agents, post-jailbreak safety feedback is often assumed to serve as a reliable safeguard; however, how lingering…
- arXiv cs.AIagentsVCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience
arXiv:2609.34687v1 Announce Type: new Abstract: Spatial reasoning is fundamental to embodied agents, yet it remains unclear whether spatial understanding can be carried forward to guide sequential interactions. Existing…
- arXiv cs.AIagentsResonAct: Streaming Metrics for Runtime Diagnosis and Self-Healing in Multi-Agent Systems
arXiv:2609.34701v1 Announce Type: new Abstract: Multi-agent systems (MAS) are increasingly used to automate enterprise workflows involving multiple specialized agents, external tools, and long-running task execution. Fai…
- arXiv cs.AIagentsFromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management
arXiv:2609.34710v1 Announce Type: new Abstract: Long-horizon agent benchmarks typically report how far an agent progresses, but do not identify whether its performance comes from the foundation model, scaffold, responsib…
- arXiv cs.AIagentsRSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents
arXiv:2609.34712v1 Announce Type: new Abstract: Practical deployment of large language model (LLM) agents requires strong task performance at affordable inference cost. For long-horizon agentic tasks, this performance-co…
- arXiv cs.AIresearchPDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
arXiv:2609.34715v1 Announce Type: new Abstract: Physical trajectories contain more than snapshots of a system: they also reveal how its states evolve under governing conditions. However, representation learning for param…