AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchVideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding
arXiv:2610.10183v1 Announce Type: cross Abstract: Long video understanding increasingly relies on external memory to organize massive visual streams into compact representations. However, most memory-based methods dynami…
- arXiv cs.AIagentsWhy Software Engineering Is Indispensable in the Age of Coding Agents
arXiv:2610.10226v2 Announce Type: replace-cross Abstract: Can AI make Software Engineering (SE) -- the discipline -- obsolete? And can it make software engineers -- the professionals -- redundant? This paper argues that…
- arXiv cs.AIresearchFrom Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular Classification
arXiv:2610.10227v1 Announce Type: cross Abstract: While Large Language Models (LLMs) possess rich world knowledge and impressive generalization capabilities, their direct application to tabular data classification is hin…
- arXiv cs.AIresearchLLM Persuasion Is in the Eye of the Evaluation
arXiv:2610.10232v1 Announce Type: cross Abstract: Large language models (LLMs) have already been shown to match or exceed human experts in persuasion. While their persuasive capabilities hold promise for beneficial uses…
- arXiv cs.AIresearchBeyond LLM-GA: Secure Fluid Antenna Systems with ReEvo-Designed Memetic Algorithm
arXiv:2610.10235v2 Announce Type: replace-cross Abstract: Fluid antenna systems (FASs) offer significant spatial flexibility, yet securing them against eavesdropping is critical for practical FAS deployment in military,…
- arXiv cs.AIresearchWhen Scientific Cognition Is No Longer Scarce
arXiv:2610.10241v1 Announce Type: cross Abstract: AI could change which parts of science impede progress. Consider a world in which machine systems are better, faster, and cheaper than people at most scientific work that…
- arXiv cs.AIagentsTestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble
arXiv:2610.10242v1 Announce Type: cross Abstract: SWE-agent ensembles improve issue resolution by combining candidate patches from different agents with complementary strengths. The central problem is therefore test-base…
- arXiv cs.AIresearchStationary Bias and Extrapolation in Nonlinear Two-Timescale Stochastic Approximation
arXiv:2610.10246v1 Announce Type: cross Abstract: Constant-step stochastic approximation generally has a nonzero stationary mean error that persists under time averaging. This paper studies that error for nonlinear two-t…
- arXiv cs.AIresearchLogarithmic Regret via Passive Change Detection in Piecewise-Stationary Self-Tuning Regulation
arXiv:2610.10250v1 Announce Type: cross Abstract: We study minimum-variance control of an unknown autoregressive system with exogenous inputs and coefficients that change at unknown times. Under bounded independent distu…
- arXiv cs.AIagentsQuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents
arXiv:2610.10258v1 Announce Type: cross Abstract: Quantum libraries are now critical infrastructure for quantum algorithm development, yet their correctness remains difficult to test. Existing testing techniques mainly r…
- arXiv cs.AIresearchLoomSC: Scalable Deep Subspace Clustering with Projector Factorization and Exact Spectral Reduction
arXiv:2610.10266v1 Announce Type: cross Abstract: Dense self-expression matrices and full-affinity spectral clustering limit the scalability of subspace clustering. We introduce the Latent Orthogonal Optimization Model f…
- arXiv cs.AIresearchSemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning
arXiv:2610.10304v1 Announce Type: cross Abstract: We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We introduce SemanticFold,…
- arXiv cs.AIresearchFault-tolerant foundation models
arXiv:2610.10311v1 Announce Type: cross Abstract: Emerging computer hardware often trades reliability for energy efficiency; here we show that large-language models (LLMs) can be trained to tolerate this unreliability, a…
- arXiv cs.AIresearchLLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices
arXiv:2610.10320v1 Announce Type: cross Abstract: Multiphysics continuum models are powerful tools for studying electrochemical devices, enabling in silico reactor design and resolution of local pH, potential, and concen…
- arXiv cs.AIresearchPerformance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation
arXiv:2610.10324v1 Announce Type: cross Abstract: Pretrained models for cell and nuclear instance segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inference strategy, a…
- arXiv cs.AIresearchSLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
arXiv:2610.10345v1 Announce Type: cross Abstract: Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious fine-tuning can erode refusal behavior while pres…
- arXiv cs.AIagentsMIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent
arXiv:2610.10355v1 Announce Type: cross Abstract: Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matches user intent. A global text-audio relevance sco…
- arXiv cs.AIresearchTaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity
arXiv:2610.10374v1 Announce Type: cross Abstract: A key challenge for multimodal large language models (MLLMs) is moving beyond visual recognition to constraint-aware cross-modal reasoning. This involves combining visual…
- arXiv cs.AIagentsRoboQuest: Generalist Physical Agents that Search, Inspect and Test
arXiv:2610.10388v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successful operation in an u…
- arXiv cs.AIresearchTraining Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds
arXiv:2610.10411v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel. Pa…
- arXiv cs.AIresearchQ-Learning with Scalar Adjoint Matching
arXiv:2610.10437v1 Announce Type: cross Abstract: Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. Howe…
- arXiv cs.AIresearchA Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching
arXiv:2610.10447v1 Announce Type: cross Abstract: Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and…
- arXiv cs.AIresearchPHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
arXiv:2610.10455v2 Announce Type: replace-cross Abstract: Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucina…
- arXiv cs.AIresearchComposing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning
arXiv:2610.10460v2 Announce Type: replace-cross Abstract: Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt dom…
- arXiv cs.AIresearchFoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
arXiv:2610.10462v1 Announce Type: cross Abstract: We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding. Existing long-trajectory policies may continue after a missed or slipped…
- arXiv cs.AIresearchHow assigned AI use before class shapes active student engagement in class
arXiv:2610.10463v1 Announce Type: cross Abstract: AI learning tools are rapidly entering classrooms, but evidence about whether they help students learn is mixed and rests mostly on test scores. Comparatively less resear…
- arXiv cs.AIagentsA Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
arXiv:2610.10468v1 Announce Type: cross Abstract: Deployments of research agents are moving to populations of thousands that share one pool of compute, while most current systems organize one project at a time or leave t…
- arXiv cs.AIresearchLong-WAM: Scaling the Context of World-Action Models
arXiv:2610.10528v1 Announce Type: cross Abstract: Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system…
- arXiv cs.AIresearchDecoupling Exploration from Optimization in RLVR
arXiv:2610.10536v1 Announce Type: cross Abstract: Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new…
- arXiv cs.AIresearchNever Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos
arXiv:2610.10538v1 Announce Type: cross Abstract: As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. We are capable of recalling where we left something o…
- arXiv cs.AIagentsFREIDA: A Framework for developing quantitative agent based models based on qualitative expert knowledge
arXiv:2308.00505v4 Announce Type: replace Abstract: Agent Based Models (ABMs) often deal with systems where there is a lack of quantitative data or where quantitative data alone may be insufficient to fully capture the c…
- arXiv cs.AIresearchRequirement-Based Testing: Enhancing Reinforcement Learning with Game Theory
arXiv:2407.18994v2 Announce Type: replace Abstract: We consider the automatic online synthesis of black-box test cases from functional requirements specified as automata for reactive implementations. The goal of the test…
- arXiv cs.AIresearchTowards Explainable Conversational AI for Early Diagnosis with Large Language Models
arXiv:2512.17559v2 Announce Type: replace Abstract: Healthcare systems around the world are grappling with issues such as inefficient diagnostics, rising costs, and limited access to specialists. These challenges often c…
- arXiv cs.AIresearchEpistemic Constitutionalism Or: how to avoid coherence bias
arXiv:2601.14295v5 Announce Type: replace Abstract: Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their responses can leave…
- arXiv cs.AIagentsPersuasion Propagation: Does Persuasion Change AI Agent Behavior?
arXiv:2602.00851v4 Announce Type: replace Abstract: AI agents combine normal conversation with autonomous task execution, allowing earlier context to shape how later tasks are executed. Yet studying this possibility is c…
- arXiv cs.AIresearchA Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
arXiv:2602.02639v2 Announce Type: replace Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Exist…
- arXiv cs.AIresearchPrototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting
arXiv:2603.11938v2 Announce Type: replace Abstract: Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, di…
- arXiv cs.AIresearchTeachingCoach: A Fine-Tuned Scaffolding Chatbot for Instructional Guidance to Instructors
arXiv:2603.18189v2 Announce Type: replace Abstract: Higher education instructors often lack timely and pedagogically grounded support, as scalable instructional guidance remains limited and existing tools rely on generic…
- arXiv cs.AIresearchWhere Experts Disagree, Models Fail: Detecting Implicit Legal Citations in French Court Decisions
arXiv:2603.22973v3 Announce Type: replace Abstract: Applying computational methods to law at scale requires separating genuine legal reasoning from surface similarity. We study this through a concrete task: detecting imp…
- arXiv cs.AIresearchBridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specifications
arXiv:2604.07652v2 Announce Type: replace Abstract: What-if analysis (WIA) lets users explore hypothetical scenarios by adjusting parameters, applying constraints, and scoping data through interactive interfaces. Current…
- arXiv cs.AIresearchU-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
arXiv:2604.08295v4 Announce Type: replace Abstract: As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and…
- arXiv cs.AIagentsOOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
arXiv:2604.11477v2 Announce Type: replace Abstract: The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforceme…
- arXiv cs.AIagentsTowards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs
arXiv:2604.17502v5 Announce Type: replace Abstract: Misaligned artificial agents might resist shutdown. One proposed solution is to train agents to lack preferences between different-length trajectories. The Discounted R…
- arXiv cs.AIagentsBeyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
arXiv:2605.12894v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with diverse users, including those who are unclear, impatient, or reluctant…
- arXiv cs.AIagentsAgentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
arXiv:2605.15871v2 Announce Type: replace Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approa…
- arXiv cs.AIresearchGenerative Recursive Reasoning
arXiv:2605.19376v5 Announce Type: replace Abstract: How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence ex…
- arXiv cs.AIagentsInsights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
arXiv:2605.21347v4 Announce Type: replace Abstract: Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process mi…
- arXiv cs.AIresearchPHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting
arXiv:2605.25554v2 Announce Type: replace Abstract: As a core task in intelligent transportation systems, traffic forecasting plays a critical role in urban traffic management. Accurate traffic forecasting relies on mode…
- arXiv cs.AIresearchA Resilience-as-a-Service assessment framework for coordinated disruption response in interdependent urban transit systems
arXiv:2606.08849v2 Announce Type: replace Abstract: Urban public transport disruptions require rapid response strategies, yet existing studies rarely provide a decision support framework to compare alternative disruption…
- arXiv cs.AIresearchGeometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice
arXiv:2606.22327v3 Announce Type: replace Abstract: The rapid growth of interactive Large Language Model serving has made efficient management of dynamic Key-Value cache footprints increasingly important for inference pe…