AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsTrajectory-Guided Fault Localization for Agent Skill Evolution
arXiv:2610.11858v1 Announce Type: cross Abstract: Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement,…
- arXiv cs.AIresearchEvaluating Exact Output and Checkpoint-State Prediction in Real Programs
arXiv:2610.11889v1 Announce Type: cross Abstract: We present a benchmark for predicting final output and checkpoint state from source and input alone. It extends CRUXEval-style output prediction with paired shorter- and…
- arXiv cs.AIagentsForms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation,…
- arXiv cs.AIresearchBeyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations
arXiv:2610.11907v1 Announce Type: cross Abstract: Hallucination remains a significant challenge in Large Vision-Language Models (LVLMs). Existing training-free methods generally mitigate hallucinations through contrastiv…
- arXiv cs.AIresearchFrom Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding
arXiv:2610.11918v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) increasingly incorporate explainable reasoning for emotion understanding. However, reasoning based mainly on observable af…
- arXiv cs.AIresearchNeural Decoding as Cognitive Inference
arXiv:2610.11923v1 Announce Type: cross Abstract: The brain maintains stable cognition despite continuously changing neural activity. How to extract stable cognitive states from variable neural observations remains a cen…
- arXiv cs.AIresearchStochastic Grouping Conformal Prediction for Effective Subgroup Reliability
arXiv:2610.11957v2 Announce Type: replace-cross Abstract: Conformal prediction offers a distribution-free coverage guarantee, making it especially attractive for clinical applications. Standard conformal prediction, howe…
- arXiv cs.AIagentsCan LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes
arXiv:2610.11963v1 Announce Type: cross Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adjust their workflow.…
- arXiv cs.AIresearchDataVista: Diagnosing Multimodal LLMs on Data Video Understanding
arXiv:2610.11993v1 Announce Type: cross Abstract: Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared with general video un…
- arXiv cs.AIresearchNeural Network Verification for Deep Joint Source-Channel Coding
arXiv:2610.11994v1 Announce Type: cross Abstract: Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharpl…
- arXiv cs.AIagentsAgentic-TTT: Training test-time policy for test-time training
arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO compe…
- arXiv cs.AIresearchThe Polytopal Neural Network
arXiv:2610.12004v1 Announce Type: cross Abstract: Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural fidelity, rely on pr…
- arXiv cs.AIresearchREACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
arXiv:2610.12007v1 Announce Type: cross Abstract: Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-of…
- arXiv cs.AIagentsExamining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology
arXiv:2610.12022v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external events to the causes…
- arXiv cs.AIresearchHWAM: Humanoid World Action Model With Joint State--Action Generation
arXiv:2610.12026v2 Announce Type: replace-cross Abstract: Humanoid robots are a promising platform for general-purpose manipulation. Recent Vision-Language-Action (VLA) policies learn actions directly from multimodal obs…
- arXiv cs.AIresearchTraceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems
arXiv:2610.12033v1 Announce Type: cross Abstract: Robotic systems operating over extended tasks must maintain a world state assembled from observations arriving at different times, with varying confidence and potential r…
- arXiv cs.AIresearchMPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation
arXiv:2610.12039v1 Announce Type: cross Abstract: Graph neural networks (GNNs) predict molecular properties from chemical graph data, but predictive accuracy does not explain how graph information supports an individual…
- arXiv cs.AIresearchMAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
arXiv:2610.12067v1 Announce Type: cross Abstract: Elucidating molecular structures from spectra is a foundational problem in chemical and materials characterization, yet remains challenging due to spectral ambiguity and…
- arXiv cs.AIresearchAll Verdicts are Not Equal: Rethinking LLM Judge Reliability
arXiv:2610.12083v1 Announce Type: cross Abstract: LLM-as-a-Judge is the standard paradigm for NLP evaluation, yet its systemic reliability remains poorly understood despite being widely treated as a deterministic ground…
- arXiv cs.AIresearchVINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
arXiv:2610.12104v1 Announce Type: cross Abstract: Building a capable video editor remains significantly harder than a video generator: editing requires (source, instruction, edited) triplets that are prohibitively expens…
- arXiv cs.AIresearchA Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
arXiv:2610.12113v2 Announce Type: replace-cross Abstract: Actor--critic methods in reinforcement learning control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere,…
- arXiv cs.AIresearchUsing Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation
arXiv:2610.12119v1 Announce Type: cross Abstract: Algorithm Selection is essential for efficient Constraint Programming. Over the years, many algorithm selectors based on machine learning methods have been successfully a…
- arXiv cs.AIresearchLVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views
arXiv:2610.12127v1 Announce Type: cross Abstract: Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content. Conventional 3D Gaussian Splatting never…
- arXiv cs.AIresearchScalable Hierarchical Graph Generation via Soft Community Structure
arXiv:2610.12163v1 Announce Type: cross Abstract: Generating large attributed graphs requires reproducing the topology, generating attributes jointly with the structure, and remaining scalable. Many real-world graphs exi…
- arXiv cs.AIresearchUnifying Policy Learning and State Prediction through Spatial Language Modeling
arXiv:2610.12172v1 Announce Type: cross Abstract: Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial Language Modeling, which represents…
- arXiv cs.AIresearchAI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware
arXiv:2610.12182v2 Announce Type: replace-cross Abstract: Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime surveillance the vessels cover a tiny frac…
- arXiv cs.AIagentsA Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
arXiv:2610.12183v1 Announce Type: cross Abstract: Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) a…
- arXiv cs.AIresearchVibeEdit: Image Editing with Canvas Instructions
arXiv:2610.12229v1 Announce Type: cross Abstract: In text-guided image editing, describing the desired change is often straightforward, but identifying the intended object or region can be cumbersome, especially when sev…
- arXiv cs.AIresearchFrom Prompting to Composing: A Spatial Canvas Interface for Poster Generation
arXiv:2610.12230v1 Announce Type: cross Abstract: Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dimensional sequence of…
- arXiv cs.AIresearchReSI: Recursive Safety Improvement toward Resistant and Resilient AI
arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both c…
- arXiv cs.AIresearchLa-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
arXiv:2610.12236v1 Announce Type: cross Abstract: RNA function arises from the coupling of nucleotide sequence and three-dimensional structure, motivating their joint design. Coordinating global folding with nucleotide-l…
- arXiv cs.AIresearchAdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting
arXiv:2610.12240v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains. However, most adaptation methods remain static. Existing all-in-one met…
- arXiv cs.AIresearchBatch Before You Lift: Scalable Topological Deep Learning on Large Graphs
arXiv:2610.12247v1 Announce Type: cross Abstract: Topological Deep Learning extends graph-based learning to higher-order domains, such as hypergraphs, cellular, and simplicial complexes. These domains are typically const…
- arXiv cs.AIresearchReal-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods
arXiv:2610.12249v1 Announce Type: cross Abstract: We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rather than introducing…
- arXiv cs.AIresearchHow Much Audio Is Left In An Embedding? An Inversion Audit Of Audio Encoders
arXiv:2610.12250v1 Announce Type: cross Abstract: Pretrained audio encoders are reused for downstream tasks that are often unknown when the encoder is trained, so their usefulness depends partly on which signal propertie…
- arXiv cs.AIresearchSyn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings
arXiv:2610.12256v1 Announce Type: cross Abstract: Omnimodal embeddings naturally involve both shared representations and modality-specific features across heterogeneous inputs. However, existing omnimodal embedding metho…
- arXiv cs.AIagentsDVD: Dynamic Vector Decoding for Efficient MLLM-based Perception
arXiv:2610.12266v1 Announce Type: cross Abstract: Multimodal large language models have made remarkable progress in bridging vision and language, facilitating various perception tasks essential for human-machine interact…
- arXiv cs.AIagentsUnlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants
arXiv:2610.12281v1 Announce Type: cross Abstract: Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet their functional interpretation remains a central o…
- arXiv cs.AIresearchMachine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery
arXiv:2610.12293v1 Announce Type: cross Abstract: Machine learning (ML) in high-energy nuclear physics (HENP) is entering a new stage in which physical knowledge is incorporated more directly into data analysis, simulati…
- arXiv cs.AIagentsMulti-Agent Egocentric World Model with Fine-Grained Embodied Interaction
arXiv:2610.12299v1 Announce Type: cross Abstract: Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multip…
- arXiv cs.AIresearchPrediction-Powered Data Fusion for Treatment Effect Estimation
arXiv:2610.12332v2 Announce Type: replace-cross Abstract: Randomized controlled trials (RCTs) identify treatment effects without confounding but are often small, whereas observational studies (OBS) are large but may be c…
- arXiv cs.AIresearchRiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning
arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics, capturing how local…
- arXiv cs.AIresearchContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration
arXiv:2610.12337v1 Announce Type: cross Abstract: Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting for local anatomy and variations in slice sampling…
- arXiv cs.AIresearchDistilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
arXiv:2610.12355v2 Announce Type: replace-cross Abstract: Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Existing remedies…
- arXiv cs.AIresearchARC: A Reasoning Recipe for Robot Foundation Models
arXiv:2610.12386v1 Announce Type: cross Abstract: The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale. We show that there e…
- arXiv cs.AIresearchSpaceFlow: Locally Controllable 3D Generation
arXiv:2610.12399v1 Announce Type: cross Abstract: Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally.…
- arXiv cs.AIresearchLeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
arXiv:2610.12407v1 Announce Type: cross Abstract: World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which c…
- arXiv cs.AIresearchPredicting Alignment Generalization with Value Representations
arXiv:2610.12410v1 Announce Type: cross Abstract: LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an alignment target. However, while recent post-training…
- arXiv cs.AIresearchMAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
arXiv:2610.12416v1 Announce Type: cross Abstract: Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environm…
- arXiv cs.AIagentsRoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
arXiv:2610.12424v1 Announce Type: cross Abstract: A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks c…