AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFormal Raising: Embedding Verifiable Ethical Properties into the Development of AI
arXiv:2610.25501v1 Announce Type: new Abstract: Alan Turing proposed constructing a ``child machine'' and educating it rather than directly programming an adult-like intelligent machine. Recent work on model raising revi…
- arXiv cs.AIagentsBud ContextCompact 2.0: Context Compaction for Agent Success and Accuracy with Small Language Models and Constrained Context Windows
arXiv:2610.25516v1 Announce Type: new Abstract: Agents that work for many turns outgrow the context window of the model that serves them, and on small language models (SLMs) and constrained inference systems that window…
- arXiv cs.AIresearchWhen Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice
arXiv:2610.25522v1 Announce Type: new Abstract: Conversational large language models can respond with warmth and reassurance while failing to advance the user's stated goal. We conceptualize this failure as $\textbf{goal…
- arXiv cs.AIagentsStopLoss: Teaching Agents to Predict Failure and Stop Early
arXiv:2610.25525v1 Announce Type: new Abstract: Coding agents keep working on runs that will fail verification, and asking a frontier model to watch for this is expensive in its own right. We introduce StopLoss, a small…
- arXiv cs.AIresearchFrom Clinical Risk Prediction to Operational Decisions: An Uncertainty-Aware Framework for ICU Staffing
arXiv:2610.25530v1 Announce Type: new Abstract: Advances in electronic health records (EHR) and large-scale critical care databases have enabled the development of machine learning models for the early detection of patie…
- arXiv cs.AIagentsAuditing Tool Traces in Agentic LLMs: Source Localization and Counterfactual Dependence Testing
arXiv:2610.25540v1 Announce Type: new Abstract: Agentic LLMs increasingly support scientific prediction by grounding decisions in external evidence. In biology, they promise accurate, interpretable predictions for import…
- arXiv cs.AIagentsEditing as Language: Teaching LLM Agents a Grammar for Native Context Editing
arXiv:2610.25550v1 Announce Type: new Abstract: A synopsis in novels folds a story into a few lines; a function in code gathers many steps with a single execution. Context editing is native to language itself. In this pa…
- arXiv cs.AIagentsSymbolic Constraint Agents: Mining Formal Tool-Call Constraints to Prevent Agent Errors
arXiv:2610.25552v1 Announce Type: new Abstract: Symbolic constraints (programmatic, deterministic checks for tool calls) enable deterministic verification of LLM agents' tool calls, but existing approaches primarily enfo…
- arXiv cs.AIresearchNarrow Decision Models: A System-1 Architecture for Calibrated, Typed Decisions
arXiv:2610.25553v1 Announce Type: new Abstract: System One models, introduced with TypeSafe's Jev, answer typed questions about a state with calibrated probabilities instead of generated text: choosing among options desc…
- arXiv cs.AIagentsLearning Which Device to Call: Online Tool Grounding for LLM Agents in IoT
arXiv:2610.25563v1 Announce Type: new Abstract: The Internet of Things (IoT) gives large language model (LLM) agents access to physical observations, but one requested capability is usually offered by several devices, an…
- arXiv cs.AIagentsDesign and Cross-Domain Evaluation of an Agent Execution Harness
arXiv:2610.25568v1 Announce Type: new Abstract: Completing complex tasks with language-model agents requires coordinating planning, execution, and review so the final result addresses the user's original objective. We pr…
- arXiv cs.AIresearchThe Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering
arXiv:2610.25630v1 Announce Type: new Abstract: The macroscopic capabilities of intelligent systems arise from the local interactions of many simple units. When such systems are deployed in the real world, their behaviou…
- arXiv cs.AIresearchThink, Compress, Answer: Reinforcement Learning for Multimodal Grounding via Reasoning Compression
arXiv:2610.25640v1 Announce Type: new Abstract: Extended reasoning has substantially improved multimodal large language models (MLLMs) on tasks requiring compositional and relational inference. However, multimodal ground…
- arXiv cs.AIresearchSpherical Fixed-Point Reasoners: Adaptive Loop Halting on the Hypersphere
arXiv:2610.25646v1 Announce Type: new Abstract: Looped (weight-tied) transformers enable adaptive computation by allocating more iterations to harder inputs. Fixed-Point Reasoners (FPRM) achieve this with a damped fixed-…
- arXiv cs.AIresearchHyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference
arXiv:2610.25673v1 Announce Type: new Abstract: Reliable microbial taxonomic inference is challenged by the rapid growth of newly sequenced organisms and incomplete reference coverage. While alignment- and database-drive…
- arXiv cs.AIresearchLIRQuant: An Efficient Locally Isolated Rotation Quantization Method for Large Language Models
arXiv:2610.25675v1 Announce Type: new Abstract: Post-Training Quantization (PTQ) enables efficient deployment of Large Language Models (LLMs), yet activation outliers remain a key challenge for low-bit quantization. Exis…
- arXiv cs.AIresearchNeither Over- nor Under-Constrained: Evaluating LLM Personalization under a Constraint Qualification Audit
arXiv:2610.25676v1 Announce Type: new Abstract: Accurate evaluation of LLM personalization is hindered by current evaluation paradigms that over- or under-constrain the response space, yielding frequent false rejections…
- arXiv cs.AIresearchBitFlat: Error-Localized Bitstream Design for Robust Diffusion Image Compression
arXiv:2610.25682v1 Announce Type: new Abstract: Zero-shot diffusion image compression based on reverse channel coding achieves high perceptual quality at low bitrates without retraining, yet its bitstream remains vulnera…
- arXiv cs.AIresearchWhen Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations
arXiv:2610.25683v1 Announce Type: new Abstract: Harmful fine-tuning can rapidly erode the safety alignment of large language models, creating substantial risks when aligned models are adapted to downstream tasks. Existin…
- arXiv cs.AIagentsToolOPD: Credit-Aware On-Policy Distillation for Tool-Use Agents
arXiv:2610.25693v1 Announce Type: new Abstract: On-policy distillation (OPD) enhances the capabilities of small language agents by providing dense, token-level supervision from a teacher model on student-generated trajec…
- arXiv cs.AIresearchCVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery
arXiv:2610.25697v1 Announce Type: new Abstract: Large language models have recently been used to discover heuristics through iterative program search, offering a promising approach to automated algorithm design. However,…
- arXiv cs.AIresearchFrom Black Box to Controller: Inference-Time Steering of LLM via Feature Amplification
arXiv:2610.25700v1 Announce Type: new Abstract: Inference-time steering is crucial for deploying Large Language Models (LLMs) in real-world applications, where they must flexibly adjust behavior preferences. For instance…
- arXiv cs.AIagentsWhose Credential Is It? How Owner Attribution in Agent MemoryShapes Cross-User Account Misuse
arXiv:2610.25707v1 Announce Type: new Abstract: Shared long-term memory lets an LLM agent serving one user inadvertently retrieve another user's credentials, but it is unclear when such exposure leads to actual harm. We…
- arXiv cs.AIresearchPFedQFT: Personalized Federated Quantum-Inspired Fine-Tuning for Medical Large Language Models
arXiv:2610.25712v1 Announce Type: new Abstract: Medical data remain fragmented across institutional silos because of privacy, governance, and ownership constraints. Federated learning enables medical institutions to adap…
- arXiv cs.AIresearchFine-Grained Units, Flat Decisions: Hierarchical Micro-Expert Pruning for Mixture-of-Experts Models
arXiv:2610.25717v1 Announce Type: new Abstract: Micro-expert pruning reduces the capacity of mixture-of-experts (MoE) models by removing coupled channels within routed experts. However, finer pruning granularity alone do…
- arXiv cs.AIagentsTimelineAgent: An LLM-based Framework for Query-Centric Event Timeline Extraction Across Multiple Documents
arXiv:2610.25733v1 Announce Type: new Abstract: Query-centric cross-document event timeline extraction aims to construct event timelines from multiple documents under diverse query focuses. The task is very challenging d…
- arXiv cs.AIresearchActTime: Action-Conditioned World Modeling for Time Series
arXiv:2610.25764v1 Announce Type: new Abstract: Time-series models increasingly condition on known future inputs. In controlled systems, some of these inputs are actions that can be changed, compared, and optimized befor…
- arXiv cs.AIresearchTRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Prediction
arXiv:2610.25765v1 Announce Type: new Abstract: Accurate inpatient risk prediction requires modeling heterogeneous clinical evidence that accumulates irregularly over time. This challenge spans in-hospital mortality, pro…
- arXiv cs.AIagentsEvalRx: Agentic Diagnosis and Verified Repair of Foundation Models
arXiv:2610.25767v1 Announce Type: new Abstract: Model evaluation reveals where models fail, but rarely why or whether a proposed fix genuinely works. We introduce EvalRx, an open-source agentic framework for statisticall…
- arXiv cs.AIagentsFrom Trace to Fix: Residual Task State in Long-Horizon Agents
arXiv:2610.25776v1 Announce Type: new Abstract: Recovering from failures in long-horizon, stateful language agents is challenging because the action introducing a defect, the symptom exposing it, and the persistent state…
- arXiv cs.AIagentsStanding on the Shoulders of Giants: Enhancing LLM Agents for Automated Fact-Checking with Human Expert Skills
arXiv:2610.25777v1 Announce Type: new Abstract: Automated fact-checking (AFC) systems powered by large language model (LLM) agents still face challenges in evidence retrieval and claim verification. Existing approaches i…
- arXiv cs.AIagentsOpenSaC: A Python Library for Search as Code in Deep Research Agents
arXiv:2610.25779v1 Announce Type: new Abstract: Deep research agents investigate complex questions through iterative search, source examination, and evidence synthesis. A conventional workflow alternates reasoning with i…
- arXiv cs.AIresearchCan LLM User-Proxies Stand In for Humans in Reliance Measurement? Replicating Rel-A.I. with Simulated Users
arXiv:2610.25788v1 Announce Type: new Abstract: Can language-model user proxies reproduce human reliance on an AI answer across contexts? Published simulated-user studies do not establish validity for this partial-answer…
- arXiv cs.AIresearchSAR: Learning Global Item-Space Matching and Geometry-Aware Placement Ranking for Buffered Online 3D Bin Packing
arXiv:2610.25795v1 Announce Type: new Abstract: Online 3D bin packing with a bounded buffer requires irreversible item-selection and placement decisions under limited knowledge of future arrivals. Feasibility alone is in…
- arXiv cs.AIresearchWhen to Stop Asking: Factor Coverage Bias and LLM Determinability Judgments with Underspecified Information in Medicine
arXiv:2610.25819v1 Announce Type: new Abstract: Clinical decision-making often begins with underspecified information and requires not only gathering missing information but also knowing when to stop. This calls for judg…
- arXiv cs.AIresearchWhen Retrieval Partially Conflicts with Skills: Understanding Procedural Hallucination in Language Models
arXiv:2610.25827v1 Announce Type: new Abstract: Language models increasingly use skills that provide reusable instructions and procedures for task execution. After a relevant skill has been selected, the model may need t…
- arXiv cs.AIagentsFrontierRefactor: Benchmarking Multi-Scale Performance-Oriented Codebase Refactoring
arXiv:2610.25834v1 Announce Type: new Abstract: Autonomous codebase refactoring requires coding agents to restructure working software while strictly preserving externally observable behavior and prioritizing execution p…
- arXiv cs.AIresearchNot Every Rollout Needs Distillation: Correctness-Filtered On-Policy Self-Distillation
arXiv:2610.25842v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) supervises student-generated trajectories with a reference-conditioned version of the same base model. We ask whether every trajectory su…
- arXiv cs.AIresearchA Cue's Hidden Price: Auditing Seller Influence on AI Shoppers
arXiv:2610.25843v1 Announce Type: new Abstract: Large language models are increasingly asked to shop on a user's behalf, which lets seller-controlled content such as badges, endorsements, and framing steer what they reco…
- arXiv cs.AIagentsMASIF: Implicit Failures for Process Observability in Multi-Agent Systems
arXiv:2610.25852v1 Announce Type: new Abstract: Multi-agent systems (MAS) can complete a task despite local execution errors that are corrected, bypassed, or carried forward without individually determining its outcome.…
- arXiv cs.AIagentsAre Self-Evolving Agents Continual Learners?
arXiv:2610.25858v1 Announce Type: new Abstract: Large language model agents are often deployed in environments where new knowledge, tools, and workflows keep arriving. Such an agent is therefore expected to adapt continu…
- arXiv cs.AIresearchMinimum-Cost Robust Evidence Certificates for Horn Reasoning under Correlated Source Failures
arXiv:2610.25865v1 Announce Type: new Abstract: A small justification for a rule-based conclusion may disappear when a source is withdrawn, and multiple derivations need not provide independent evidence. We study minimum…
- arXiv cs.AIresearchBenefit-Targeted Routing and Bounded Revision for LLM-Based Evidence Screening in Manufacturing Supplier Discovery
arXiv:2610.25867v1 Announce Type: new Abstract: An evidence-review system must allocate additional model judgments and control their use. We study these software decisions on 6,164 frozen manufacturing source-task pairs.…
- arXiv cs.AIresearchCODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning
arXiv:2610.25871v1 Announce Type: new Abstract: Recent advances in multimodal foundation models have demonstrated strong performance across diverse clinical tasks. However, existing approaches predominantly operate at th…
- arXiv cs.AIresearchMotor compound fault diagnosis using an attention-based cross-talk architecture
arXiv:2610.25893v1 Announce Type: new Abstract: As physical AI increasingly relies on sensing to understand physical systems, reliable condition monitoring of industrial machinery has become more important. Motors are ub…
- arXiv cs.AIagentsWhen Should AI Chime In? Benchmarking Timely Contribution of Proactive Agents in Multi-Party Chat
arXiv:2610.25896v2 Announce Type: replace Abstract: Proactive agents can support group collaboration by surfacing useful information without waiting to be asked, but even relevant contributions can be disruptive if poorl…
- arXiv cs.AIagentsTESS: LLM-guided Translation, Exploration, Simulation, and Search for Embodied Task Planning
arXiv:2610.25930v1 Announce Type: new Abstract: In this work we focus on the problem of embodied task planning, which requires an agent to accomplish a complex task by separating it into atomic actions. Recent studies ha…
- arXiv cs.AIagentsEvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver
arXiv:2610.25931v2 Announce Type: replace Abstract: EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact. The user starts a run by describing a…
- arXiv cs.AIresearchGlobal probabilistic forecasting of air pollution
arXiv:2610.25941v1 Announce Type: new Abstract: Fine particulate matter (PM2.5) refers to particulate matter with an aerodynamic diameter of 2.5 micrometre or less. It comes from human activities, such as traffic and ind…
- arXiv cs.AIagentsClaim Laundering: When Agent Decision Models Trust Records Over Reality
arXiv:2610.25947v1 Announce Type: new Abstract: Agent decision models select actions in a single forward pass from inputs that combine environmental observations with the agent's own record of previous actions. When an a…