AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsStepSafe: Learning Timely Intervention with Context-Aware Safety Reasoning
arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and interactions among agents…
- arXiv cs.AIresearchMSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data
arXiv:2610.20965v1 Announce Type: new Abstract: Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data. However, this paradigm introduces a fund…
- arXiv cs.AIresearchDeep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation
arXiv:2610.21008v1 Announce Type: new Abstract: Deep Reinforcement Learning (DRL) offers learned job selection for High-Performance Computing (HPC), but performance against heuristics alone does not establish value beyon…
- arXiv cs.AIresearchFailure Is the Mother of Success: Recovering Supervision with Grounding Hindsight
arXiv:2610.21018v1 Announce Type: new Abstract: When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from exactly the problems i…
- arXiv cs.AIresearchRecursive Reward Improvement via Adversarial Meta-Prompt Evolution
arXiv:2610.21040v1 Announce Type: new Abstract: Recursive Self-Improvement (RSI) has gained wide attention for its ability to work with limited data. In a proposer-solver loop, a proposer model writes training tasks and…
- arXiv cs.AIagentsLearning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents
arXiv:2610.21045v1 Announce Type: new Abstract: Tool-using language agents must revise prepared actions when evidence changes or authority is revoked. Selective withdrawal means suspending affected actions, preserving su…
- arXiv cs.AIagentsAthanor: An Agent-Native System for Autonomous Post-Training Research
arXiv:2610.21055v1 Announce Type: new Abstract: Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence. We study a weaker form that can be measured today: f…
- arXiv cs.AIagentsOmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics
arXiv:2610.21074v1 Announce Type: new Abstract: Computational biologists increasingly delegate substantial analyses to AI agents in long-horizon, multi-turn sessions, yet most benchmarks of agents' bioinformatics capabil…
- arXiv cs.AIagentsSci$\Pi$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
arXiv:2610.21082v1 Announce Type: new Abstract: Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, but reliable autonomous research also requires scientifi…
- arXiv cs.AIagentsProbe-and-Resume: When and How to Evaluate Agent Execution
arXiv:2610.21088v1 Announce Type: new Abstract: Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach in terminal-based co…
- arXiv cs.AIagentsMemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning
arXiv:2610.21091v2 Announce Type: replace Abstract: Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarante…
- arXiv cs.AIagentsPlanning Commitment of LLM under Partial Observability
arXiv:2610.21108v2 Announce Type: replace Abstract: LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a long plan based…
- arXiv cs.AIagentsKolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
arXiv:2610.21109v1 Announce Type: new Abstract: When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions? For solving long-horizon tasks, humans place greater importance on…
- arXiv cs.AIresearchCleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF
arXiv:2610.21138v1 Announce Type: new Abstract: Feedback noise is pervasive in preference data, arising from subjective human judgments, annotation mistakes, and imperfect LLM judges. Standard reward modeling trained on…
- arXiv cs.AIagentsAll-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents
arXiv:2610.21147v2 Announce Type: replace Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and lengthy documents. H…
- arXiv cs.AIagentsGRADS: Graph-Regulated Agentic Data Synthesis with Controllable Difficulty
arXiv:2610.21167v1 Announce Type: new Abstract: Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet multi-hop, long-horizon tasks remain challenging. Synthetic data gene…
- arXiv cs.AIagentsMemScope: Evolving Agent Memory Architectures through Localized Code Repair
arXiv:2610.21170v1 Announce Type: new Abstract: Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their adaptability across…
- arXiv cs.AIagentsAgentEval: Evidence-Bounded Assessment of Stateful Agents
arXiv:2610.21177v1 Announce Type: new Abstract: Task completion alone does not determine whether a stateful agent satisfied its obligations, and a recorded judgment does not guarantee that its supporting evidence remains…
- arXiv cs.AIresearchDoes Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent Reasoning
arXiv:2610.21182v1 Announce Type: new Abstract: Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models additional steps to compute before answering. It remains unclear what…
- arXiv cs.AIresearchMine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
arXiv:2610.21185v1 Announce Type: new Abstract: Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so. We introduce MINE-SAMPLE-RENDER…
- arXiv cs.AIresearchCondition-Contrastive Extrapolation for On-Policy Distillation of Language Models
arXiv:2610.21195v1 Announce Type: new Abstract: On-policy distillation (OPD) improves a student language model by training on its own generated trajectories with supervision from a stronger teacher. However, when conditi…
- arXiv cs.AIagentsWho May Release an Agent's Promise? Standing over Commitments in Multi-Party Chat
arXiv:2610.21203v1 Announce Type: new Abstract: When an assistant serving a team makes a promise to Alice, who may cancel it? We call this standing: only the creditor (the person owed) or someone the creditor or operator…
- arXiv cs.AIresearchEntertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally
arXiv:2610.21204v1 Announce Type: new Abstract: When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but…
- arXiv cs.AIresearchRubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation
arXiv:2610.21214v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from…
- arXiv cs.AIagentsAutoOnboarder: Autonomously Onboarding LLM Agents
arXiv:2610.21218v1 Announce Type: new Abstract: Agentic large language models have been documented to lose reasoning capability when placed inside a harness, the software that mediates their observations and actions. To…
- arXiv cs.AIagentsAuditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures
arXiv:2610.21270v1 Announce Type: new Abstract: Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting, or late, not only accurate answers on static inputs. We instantia…
- arXiv cs.AIagentsDiviner: Agentic RCA with Human-Governed Adaptation for Large-Scale Infrastructure
arXiv:2610.21281v1 Announce Type: new Abstract: Root-cause analysis (RCA) in large-scale distributed systems is challenging because a single symptom can cross service, data, configuration, compute, and organizational bou…
- arXiv cs.AIagentsMallea: Building, Steering, and Memorizing Worlds with Coding Agent
arXiv:2610.21283v1 Announce Type: new Abstract: Code world models represent world dynamics through explicit state and executable rules. We investigate how to coordinate object representations, behavioral revisions, and v…
- arXiv cs.AIresearchThe Density of Thought: Predicting and Steering Reasoning in Large Language Models
arXiv:2610.21286v1 Announce Type: new Abstract: We investigate whether variation in information density across chain-of-thought (CoT) reasoning steps predicts answer correctness and can serve as a controllable inference-…
- arXiv cs.AIagentsBias Control and Injection for Multi-Agent Aggregation
arXiv:2610.21290v1 Announce Type: new Abstract: Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Re…
- arXiv cs.AIresearchMoney-Mule Detection as a Relational Learning Problem: A Study on the RBIH NFPC Dataset
arXiv:2610.21314v1 Announce Type: new Abstract: Money-mule networks move criminal funds through many small transfers, each of which looks ordinary on its own. What marks an account as a mule lies outside any single trans…
- arXiv cs.AIagentsConstrained Multi-Agent Reinforcement Learning in Imagination
arXiv:2610.21319v1 Announce Type: new Abstract: Predicting cost in a multi-agent world model moves most constrained policy updates into imagination: the stronger model-free baseline needs $10$ to $20$ times CA-MAMBA's in…
- arXiv cs.AIagentsDocPilot: Interactive Agent Orchestration and Training for Long Visual Document Understanding
arXiv:2610.21327v1 Announce Type: new Abstract: Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document content, and reason over…
- arXiv cs.AIresearchQuantum Versus Classical Machine Learning for Neuropsychiatric Disorders: A Feature-Matched Multi-Cohort Evaluation
arXiv:2610.21344v1 Announce Type: new Abstract: Resting-state functional connectivity is widely used in machine learning-based classification of neuropsychiatric disorders. Quantum machine learning models have been propo…
- arXiv cs.AIagentsARGUS: An Agenda-Driven Framework for Reliable User Simulation
arXiv:2610.21346v1 Announce Type: new Abstract: High-fidelity user simulators are essential for evaluating and training agents in interactive environments. However, current LLM-based simulators struggle with reliability…
- arXiv cs.AIagentsFedSkillGit: Federated Skill Evolution via Version Control
arXiv:2610.21348v1 Announce Type: new Abstract: Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deployments, this experienc…
- arXiv cs.AIresearchHierarchical Graph Convolutional Network Approach for Detecting Low-Quality Documents
arXiv:2610.21350v1 Announce Type: new Abstract: Consistency within a document is a crucial feature indicative of its quality. Recently, within the vast amount of information produced across various media, there exists a…
- arXiv cs.AIresearchLearning to Reason with Selective Internal Feedback
arXiv:2610.21392v1 Announce Type: new Abstract: Reinforcement learning from internal feedback can improve language models without ground-truth answers or external verifiers. However, confidence and correctness can diverg…
- arXiv cs.AIresearchSelf-Guided LLM Reasoning for Error Diagnosis in Vehicle Routing Problems
arXiv:2610.21393v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental to many real-world applications. Recent advances in large language models (LLMs) have spurred progress in solving these NP-h…
- arXiv cs.AIresearchWatts If? A Benchmark for Counterfactual Reasoning About the AI Data Center Buildout
arXiv:2610.21397v1 Announce Type: new Abstract: An AI data center is committed years before it draws a watt: a few discrete choices (grid or on-site gas, evaporative or dry cooling, which county to file in) fix its capit…
- arXiv cs.AIagentsMemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM Agents
arXiv:2610.21405v1 Announce Type: new Abstract: Long-term memory has become a crucial component of large language model (LLM) agents, with most research focusing on retrieving relevant information accurately and efficien…
- arXiv cs.AIagentsJev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows
arXiv:2610.21411v2 Announce Type: replace Abstract: Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded de…
- arXiv cs.AIagentsJevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs
arXiv:2610.21412v1 Announce Type: new Abstract: Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step,…
- arXiv cs.AIagentsDo Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents
arXiv:2610.21424v2 Announce Type: replace Abstract: Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Representation for Age…
- arXiv cs.AIresearchLearning from Interaction Experience via Localized Context Distillation
arXiv:2610.21427v1 Announce Type: new Abstract: Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offers a promising path:…
- arXiv cs.AIresearchIncentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction
arXiv:2610.21449v2 Announce Type: replace Abstract: Large language models (LLMs) can reason over both structured measurements and free-text records, which makes them attractive for emergency department (ED) prediction. H…
- arXiv cs.AIresearchOntology Refinement with Embeddings and LLMs: A Case Study on CASTON
arXiv:2610.21466v1 Announce Type: new Abstract: Ontologies are widely used to represent and organize complex knowledge in domains such as biomedicine and healthcare. However, constructing reliable ontologies remains chal…
- arXiv cs.AIresearchTool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes
arXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to free-form patient notes…
- arXiv cs.AIresearchAI-Driven Disaster Response and Displacement Monitoring
arXiv:2610.21482v1 Announce Type: new Abstract: ARTIFICIAL INTELLIGENCE (AI) has demonstrated its potential across a wide range of humanitarian tasks, offering scalable and data-driven solutions to some of the world's mo…
- arXiv cs.AIresearchFlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors
arXiv:2610.21483v1 Announce Type: new Abstract: Large language models can produce fluent answers that the supplied context does not support. A compact frozen proxy model can detect such answers by reading the context and…