AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchOrderGPT: Generation Order as a Learnable Modeling Choice
arXiv:2610.25949v1 Announce Type: new Abstract: Generative modeling of discrete data has two popular paradigms: autoregressive models such as GPT, which factorize a sequence in a left-to-right (L2R) order, and masked dif…
- arXiv cs.AIagentsCXBench: A Benchmark for Process-Compliant LLM Agents in Regulated Customer-Experience Workflows
arXiv:2610.25954v1 Announce Type: new Abstract: Tool-using language agents increasingly perform regulated customer-service workflows, where a correct final state is insufficient: agents must also provide disclosures, obt…
- arXiv cs.AIagentsProductive State-Space Exploration for Multi-turn RL in LLM Agents
arXiv:2610.25957v1 Announce Type: new Abstract: Reinforcement Learning (RL) for Large Language Model (LLM) agents in multi-turn, long-horizon environments remains challenging due to inefficient action selection and repet…
- arXiv cs.AIagentsEmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
arXiv:2610.25959v2 Announce Type: replace Abstract: Building embodied agents that can perceive, reason, and act across diverse 3D worlds is a central research direction toward artificial general intelligence. Yet most ex…
- arXiv cs.AIresearchABACUS: Program-Guided Multistep Reasoning over Frozen Judgment Models
arXiv:2610.25963v1 Announce Type: new Abstract: Judgment models answer semantic questions by scoring a finite set of candidate outcomes. Can reusable programs turn these local decisions into powerful multistep reasoning?…
- arXiv cs.AIresearchGLOBE: Geometry-Led Online Behavioral Early Exit via Unit-Sphere Trajectories
arXiv:2610.25970v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning can improve problem solving, but models often keep generating after the correct answer is already reachable; the extra steps raise serving…
- arXiv cs.AIresearchOn the Benefits of Uncertainty Estimation for Species Classification: A Case Study on Optimizing Expert re-Annotation
arXiv:2610.25977v1 Announce Type: new Abstract: Automated identification of diatoms from microscopic images is a cornerstone of large-scale freshwater biomonitoring, yet the high diversity of species and strong class imb…
- arXiv cs.AIresearchGraphEvoResearcher: Graph-Aware Training-Free Self-Reflective Reasoning for Cost-Bounded Multi-Hop Question Answering
arXiv:2610.25978v1 Announce Type: new Abstract: Multi-hop question answering (QA) requires models to chain intermediate conclusions while remaining cost-aware. Existing training-free self-reflective protocols (generate -…
- arXiv cs.AIagentsClueFlow: Learning Long-Horizon Search through Attributed Research-State Transitions
arXiv:2610.25980v1 Announce Type: new Abstract: Long-horizon search requires agents to acquire relevant evidence and integrate it into an evolving research state. Existing methods maintain research states to guide explor…
- arXiv cs.AIagentsMap-Distribution Mixture-of-Experts for Multi-Agent Pathfinding
arXiv:2610.25991v1 Announce Type: new Abstract: Designing capable neural policies for multi-agent pathfinding (MAPF), which map local observations to action distributions, represents an important challenge in multi-agent…
- arXiv cs.AIagentsProcedural Memory for Language Agents: A Neurosymbolic Perspective on Explicit Goal Structure
arXiv:2610.25996v1 Announce Type: new Abstract: Large language models remain unreliable on long-horizon tasks requiring procedural reasoning. We argue that a key cause is the absence of explicit procedural memory: access…
- arXiv cs.AIresearchTimesJev: Thinking Fast on Time Series with System 1 Sufficiency
arXiv:2610.26002v1 Announce Type: new Abstract: Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thoug…
- arXiv cs.AIresearchUnderstanding When Reflective Prompt and Skill Optimization Helps on Locally Served Reasoning Models: A Two-Model Study of GEPA and SkillOpt
arXiv:2610.26020v1 Announce Type: new Abstract: Reflective text-space optimizers such as GEPA and SkillOpt have reported large gains on frontier and mid-size models. We test replication across two reasoning-native target…
- arXiv cs.AIagentsAuDQ: Auditable Data Quality through Agentic Rule Discovery
arXiv:2610.26031v1 Announce Type: new Abstract: High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the…
- arXiv cs.AIagentsDecision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems
arXiv:2610.26035v1 Announce Type: new Abstract: Decision models, such as the commercial Jev, are language models that return one probability for each option of a question instead of generating text. We present Decision4R…
- arXiv cs.AIresearchFinSafeGuard: A Quality-Driven Synthetic Dataset for Financial AI Safety
arXiv:2610.26066v1 Announce Type: new Abstract: Generating high-quality synthetic datasets at scale remains a fundamental challenge for training specialized AI systems in data-scarce domains. We present a comprehensive m…
- arXiv cs.AIagentsCUA-Lite: An Open Platform for Computer Use Agents
arXiv:2610.26071v1 Announce Type: new Abstract: Open resources for computer use agents (CUAs) -- environments, datasets, and models -- remain scattered: without a standard, these resources cannot be integrated and scaled…
- arXiv cs.AIagentsFrom Code to Playable Systems: CEGame-Bench for Long-Horizon Game Creation Agents
arXiv:2610.26098v1 Announce Type: new Abstract: A game ships when a player can launch it, finish it, and return to a saved world, none of which a successful build guarantees, yet game-creation agents are mostly tested on…
- arXiv cs.AIagentsReliable Before Profitable: QuantHarness for Governing Financial Strategy Development with LLM Agents
arXiv:2610.26101v1 Announce Type: new Abstract: LLM agents can turn natural-language financial research requests into executable and backtested strategies, but a successful run may still implement the wrong rule, use inf…
- arXiv cs.AIresearchMoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
arXiv:2610.26185v2 Announce Type: replace Abstract: Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluat…
- arXiv cs.AIresearchOn Counting Graphs for Modal Logic with Counting
arXiv:2610.26187v1 Announce Type: new Abstract: In this paper, we study the theoretical computational complexity of counting trees and graphs that are classified positively by a graph neural networks, or said equivalentl…
- arXiv cs.AIresearchLLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
arXiv:2610.26211v1 Announce Type: new Abstract: Confidentiality requirements increasingly push legal professionals toward small, on-device LLMs that keep case data in-house, used for everyday tasks such as summarization,…
- arXiv cs.AIresearchFairness or Fallacy? Mapping the Landscape of AI Bias in Disease Detection
arXiv:2610.26215v1 Announce Type: new Abstract: Artificial intelligence (AI) has several transformative effects on healthcare, like to facilitate clinicians in disease detection and to manage patient care with enhanced p…
- arXiv cs.AIresearchTowards More Granular Reasoning: Mapping the DSA Transparency Database Taxonomy to Platform Terms and Conditions Using Large Language Models
arXiv:2610.26226v1 Announce Type: new Abstract: Article 24(5) of the Digital Services Act (DSA) requires providers of online platforms to submit every content moderation decision they make, with a corresponding Statement…
- arXiv cs.AIresearchCoRS: Fast Neural Flexible Job-Shop Scheduling via Composite Interval State Reuse
arXiv:2610.26239v1 Announce Type: new Abstract: Neural solvers for the Flexible Job-Shop Scheduling Problem (FJSP) typically refresh graph representations and update feasibility after every operation--machine decision. H…
- arXiv cs.AIresearchMachina Pauliana: A neuro-symbolic approach to the actio pauliana in Dutch insolvency law
arXiv:2610.26241v1 Announce Type: new Abstract: Applying a legal provision frequently requires both structured rule-based reasoning and sensitivity to open-textured terms developed in case law. The actio pauliana of Arti…
- arXiv cs.AIresearchBeyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation Models
arXiv:2610.26251v1 Announce Type: new Abstract: Static public benchmarks for time series foundation models (TSFMs) typically have fixed and narrow test distributions. Their repeated reuse encourages benchmark-specific tu…
- arXiv cs.AIresearchLOCU: Lowdin-Orthogonalized Constraint Updates for Multi-Constraint Policy Optimization
arXiv:2610.26256v1 Announce Type: new Abstract: We investigate multi-constraint policy optimization in constrained Markov decision processes (CMDPs), where interactions among constraint gradients often yield ill-conditio…
- arXiv cs.AIresearchREFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
arXiv:2610.26261v3 Announce Type: replace Abstract: RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing st…
- arXiv cs.AIagentsThe Scheduler Is a Hidden Retriever: How Asynchrony Shapes Evidence Acquisition in Search Agents
arXiv:2610.26310v1 Announce Type: new Abstract: Language-model agents increasingly solve complex tasks through parallel reasoning and asynchronous information gathering. Controlled replay across two model families and th…
- arXiv cs.AIresearchSelective Transfer through Sequence Distillation: From Benchmark Knowledge to Backdoor Behaviour
arXiv:2610.26311v1 Announce Type: new Abstract: Knowledge distillation is widely used to transfer capabilities from teacher models to student models, but recent work shows that it can also transfer unintended teacher pro…
- arXiv cs.AIresearchStrucChunk: Structure-Aware Retrieval for Legal Document RAG
arXiv:2610.26313v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) can ground LLM outputs in domain-specific knowledge, but legal documents are hard: standard chunking fragments hierarchical argument st…
- arXiv cs.AIagentsThe Control Layer Behind Rule-Following Agents Trading Across Market Conditions
arXiv:2610.26324v2 Announce Type: replace Abstract: Trading discipline often fails people. Our study tested whether four AI trading agents followed their strategies and risk rules. Offering traders the evidence and an ag…
- arXiv cs.AIresearchA Generic On-Board AI Processing Chain for Earth Observation: From Application Development to Embedded Deployment and Mission-Level Orchestration
arXiv:2610.26340v1 Announce Type: new Abstract: Earth observation satellites acquire more data than they can downlink. Extracting information on board with artificial intelligence (AI) turns the satellite into a data-red…
- arXiv cs.AIagentsVibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement
arXiv:2610.26342v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) requires agents to diagnose system bottlenecks and coordinate improvements across training and inference. We refer to the agents' capab…
- arXiv cs.AIresearchCARRS: A Constraint-Aware, Real-Time Routing System for Emergency Vehicles in Urban Environments
arXiv:2610.26346v1 Announce Type: new Abstract: Emergency vehicles such as police vehicles, fire engines, and ambulances require a stable and efficient route optimization to reach life-critical events in the shortest tim…
- arXiv cs.AIresearchGAIDA: Generative AI for Human-in-the-Loop Document Annotation
arXiv:2610.26362v1 Announce Type: new Abstract: Document annotation is a fundamental yet labor-intensive step in building document information extraction systems. While Optical Character Recognition (OCR) and Large Langu…
- arXiv cs.AIagentsAutonomous intelligence for mining productivity: a multi-agent AI approach to operational value creation
arXiv:2610.26369v1 Announce Type: new Abstract: Integrated Remote Operation Centres (IROCs) are emerging as the architectural frontier of Industry 4.0 for capital-intensive sectors such as mining, oil and gas, and energy…
- arXiv cs.AIresearchBOSS: Token-Budgeted Online Sampling and Selection for LLM Reasoning
arXiv:2610.26383v1 Announce Type: new Abstract: Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We stud…
- arXiv cs.AIresearchAnswer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization
arXiv:2610.26384v1 Announce Type: new Abstract: An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalizati…
- arXiv cs.AIresearchLocal data augmentation for imbalanced binary classification
arXiv:2610.26418v1 Announce Type: new Abstract: Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the presen…
- arXiv cs.AIresearchPhysiology-Aware Graph Attention for Early Ventricular Reentry Prediction
arXiv:2610.26430v1 Announce Type: new Abstract: Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficul…
- arXiv cs.AIagentsLearning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents
arXiv:2610.26453v2 Announce Type: replace Abstract: Self-improving agents aim to continuously improve their behavior by learning from experience after deployment. However, accumulating and reusing more experience does no…
- arXiv cs.AIagentsVeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards
arXiv:2610.26469v1 Announce Type: new Abstract: Reinforcement learning for computer-use agents increasingly relies on proactive reward agents that interact with the post-execution GUI environment to verify what recorded…
- arXiv cs.AIagentsScopeMem: Latent Memory That Learns Where to Revise Frozen GUI Agents
arXiv:2610.26503v1 Announce Type: new Abstract: Latent memory is gaining ground as a lightweight history supplement for GUI agents. It supplies history to a frozen vision-language model via prefix vectors trained with st…
- arXiv cs.AIresearchRouterWorld: Scaling Conversational AI with Latency-Aware LLM Routing
arXiv:2610.26511v1 Announce Type: new Abstract: Conversational AI systems built on Large Language Models (LLMs) require routing mechanisms that balance answer quality and response latency at scale. However, existing LLM…
- arXiv cs.AIresearchToward Structured Financial Foundation Models
arXiv:2610.26516v1 Announce Type: new Abstract: Foundation models promise reusable capabilities and step-change performance gains across tasks. In finance, large-scale pretraining of domain-specialized foundation models…
- arXiv cs.AIresearchBeyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation
arXiv:2610.26524v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as user simulators, but can they faithfully reproduce an individual's behavior and decision logic over time? We inves…
- arXiv cs.AIagentsA Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes
arXiv:2610.26528v1 Announce Type: new Abstract: Knowledge graphs (KGs) are increasingly used in autonomous driving (AD) to make traffic scene entities and relations explicit for prediction and reasoning. Existing traffic…
- arXiv cs.AIresearchBreaking Diffusion: Parallel Reasoning with Draft Refinement
arXiv:2610.26542v1 Announce Type: new Abstract: Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually pla…