AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchHyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics
arXiv:2610.15760v1 Announce Type: cross Abstract: Multiscale structure is central to time series forecasting: temporal signals contain slowly varying trends, intermediate seasonal patterns, and high-frequency residuals.…
- arXiv cs.AIagentsA Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
arXiv:2610.15765v1 Announce Type: cross Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designed for human end user…
- arXiv cs.AIagentsSurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation
arXiv:2610.15766v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) and vision--language--action models have provided robots with new capabilities for long-horizon task understanding and pla…
- arXiv cs.AIresearchAn Explainable System for Offensive Content Detection in Nastaliq Urdu: Corpus Curation, Transformer Benchmarking, and Word-Level Attribution
arXiv:2610.15795v1 Announce Type: cross Abstract: Automated moderation systems are deployed at scale, yet they remain opaque to the users and moderators affected by their decisions, and their coverage is almost entirely…
- arXiv cs.AIresearchAdaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning
arXiv:2610.15810v1 Announce Type: cross Abstract: The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language models (MLLMs) on gen…
- arXiv cs.AIagentsLLM Value Functions for Credit Assignment in Agentic RL
arXiv:2610.15840v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assigning credit to individ…
- arXiv cs.AIresearchPersonalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction
arXiv:2610.15864v1 Announce Type: cross Abstract: Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to recommend, where each…
- arXiv cs.AIresearchWhat the Model Cannot See: Covert and Provable Text Invisibility in LLMs
arXiv:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answering, and left unflagged…
- arXiv cs.AIresearchVariance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards
arXiv:2610.15888v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards spends much of its rollout budget on states that yield no learning signal. We recast this as a question about the sampling…
- arXiv cs.AIresearchLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition
arXiv:2610.15891v1 Announce Type: cross Abstract: Predictive video representations do not by themselves specify how a multimodal system should handle missing sensors. We transfer frozen V-JEPA2 features to a set of heter…
- arXiv cs.AIresearchMake Every Expansion Count: Learning to Search Efficiently in LLM Code Repair
arXiv:2610.15894v1 Announce Type: cross Abstract: Large language model (LLM) code-repair systems fix faulty programs by repeatedly generating and testing revisions. Each revision is costly, making the choice of which rep…
- arXiv cs.AIresearchReview Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines
arXiv:2610.15897v2 Announce Type: replace-cross Abstract: Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result. Reviewing another model's answer is usua…
- arXiv cs.AIresearchGen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion
arXiv:2610.15900v1 Announce Type: cross Abstract: We present Gen Through the Lens, a camera-controllable image-to-video generation framework that synthesizes videos from a given reference image while enabling realistic a…
- arXiv cs.AIresearchRINO: Renormalization Group Distillation with No Labels
arXiv:2610.15919v1 Announce Type: cross Abstract: Supervised machine learning in high-energy physics (HEP) requires training on labeled simulations of particle collisions, which are known to be unfaithful to the underlyi…
- arXiv cs.AIagentsScalable Weak-to-Strong Verifier Hardening for Agent Environments
arXiv:2610.15924v1 Announce Type: cross Abstract: Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. Verifiers can be attac…
- arXiv cs.AIresearchDiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion Policies
arXiv:2610.15932v1 Announce Type: cross Abstract: Computing equilibria in high-dimensional continuous games requires learning and representing rich, multi-modal strategy distributions, something conventional neural polic…
- arXiv cs.AIresearchHardware-Assisted Multi-Stage Ransomware Detection with Adaptive Machine Learning
arXiv:2610.15951v1 Announce Type: cross Abstract: Ransomware is a fast-escalating privacy threat causing significant financial and data losses worldwide. As attacks grow more sophisticated, traditional static signatures…
- arXiv cs.AIresearchUnfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
arXiv:2610.15961v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now routinely fine-tune…
- arXiv cs.AIagentsEmbedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs
arXiv:2610.15976v1 Announce Type: cross Abstract: This paper investigates a new role of randomness in stochastic policies--as a medium for embedding and communicating information. Specifically, we consider an agent inter…
- arXiv cs.AIresearchAutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RAN
arXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Network (O-RAN) testing.…
- arXiv cs.AIresearchWhen Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits
arXiv:2610.16020v1 Announce Type: cross Abstract: Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers. We ask under what assumptions such compe…
- arXiv cs.AIagentsOf Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
arXiv:2610.16027v1 Announce Type: cross Abstract: Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed error may be inherited…
- arXiv cs.AIresearchOT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation
arXiv:2610.16038v1 Announce Type: cross Abstract: E-commerce user preferences evolve dynamically within sessions, exhibiting concurrent and multi-centric interest distributions. While existing multimodal sequential recom…
- arXiv cs.AIagentsWhen Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems
arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to one authorized agent…
- arXiv cs.AIresearchAutoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation
arXiv:2610.16041v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success across a wide range of language tasks. At their core, autoregressive LLMs are conditional probability models…
- arXiv cs.AIresearchAI Representations of Mental Health Stigma: Quantifying the Gap Between AI Estimations and Human Perceptions Across Gender Groups Using GPT-Based LLMs
arXiv:2610.16042v1 Announce Type: cross Abstract: The increasing use of artificial intelligence (AI) in mental health applications raises concerns about its potential to internalize and perpetuate societal biases. This r…
- arXiv cs.AIresearchAdaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection
arXiv:2610.16049v1 Announce Type: cross Abstract: Existing audio deepfake detection (ADD) methods frequently exhibit limited generalization, as fixed bottleneck architectures fail to adapt to the heterogeneous informatio…
- arXiv cs.AIagentsWhen Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark
arXiv:2610.16067v2 Announce Type: replace-cross Abstract: Agent evaluation harnesses are software: they run a test suite, drive a test input generator, and decide outcomes with a test oracle. We audit them for defects a…
- arXiv cs.AIagentsDream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems
arXiv:2610.16071v1 Announce Type: cross Abstract: Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes. These auditors typically…
- arXiv cs.AIresearchWhere Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science
arXiv:2610.16102v2 Announce Type: replace-cross Abstract: We argue that tacit knowing is better modelled as an operating regime of a memory than as a kind of content. Our substrate is VaCoAl, an algebro-deterministic XOR…
- arXiv cs.AIresearchTowards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry
arXiv:2610.16127v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored in the Architecture, Engineering, and Construction (AEC) domain, yet their reliability in regulatory compliance rem…
- arXiv cs.AIagentsPID-Gated Continual Prompt Adaptation Under Noisy Feedback
arXiv:2610.16129v1 Announce Type: cross Abstract: Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every reported mistake can tu…
- arXiv cs.AIresearchQuery Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving
arXiv:2610.16133v1 Announce Type: cross Abstract: Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require multi-step decisions t…
- arXiv cs.AIresearchOmni-Modal LLMs Know More Than They Say
arXiv:2610.16135v1 Announce Type: cross Abstract: Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language, enabling a broader…
- arXiv cs.AIresearchUnravel: Recovering an Interactive 3D Scene from a Single Image
arXiv:2610.16146v1 Announce Type: cross Abstract: We present Unravel, a training-free framework that turns a single image into an interactive 3D scene, where every object is an independent and movable asset. Existing gen…
- arXiv cs.AIresearchWildTrace: Evaluating Training Data Detection in Realistic Large-Scale LLM Post-Training
arXiv:2610.16152v1 Announce Type: cross Abstract: Although post-training significantly enhances model performance, the use of massive undisclosed data raises concerns about benchmark contamination and copyright infringem…
- arXiv cs.AIresearchFisher information and the geometry of memorization in neural networks
arXiv:2610.16161v1 Announce Type: cross Abstract: A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from idiosyncratic or eve…
- arXiv cs.AIresearchEventLens: Event-Structure Reinforcement Learning for Video Understanding
arXiv:2610.16172v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure that makes a video co…
- arXiv cs.AIresearchMP-MNCA: Morphology-Prior Masked Neighbor Cross-Attention for Efficient Spatial Domain Identification
arXiv:2610.16212v1 Announce Type: cross Abstract: Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late trai…
- arXiv cs.AIresearchSafeDSE: Joint Exploration of Safety Architecture Patterns, Mapping, and Scheduling for Dataflow Applications With Safety Arguments (Extended Version)
arXiv:2610.16213v1 Announce Type: cross Abstract: Embedded platforms increasingly host safety-related streaming functions next to less critical ones. Whether a safety architecture pattern, such as a doer/checker pair, pr…
- arXiv cs.AIagentsLook Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation
arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challenging. Existing agenti…
- arXiv cs.AIagentsAutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms
arXiv:2610.16232v1 Announce Type: cross Abstract: In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit mo…
- arXiv cs.AIresearchReflected Proximal Dynamics for Accelerated High-Accuracy Log-Concave Sampling
arXiv:2610.16248v1 Announce Type: cross Abstract: We study sampling from $\pi(x)\propto\mathrm{e}^{-V(x)}$ on $\mathbb{R}^d$, where $V$ is $\alpha$-strongly convex and $\beta$-smooth with condition number $\kappa=\beta/\…
- arXiv cs.AIagentsAvoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation
arXiv:2610.16251v1 Announce Type: cross Abstract: Deep-search agents are commonly trained by distilling tool-use trajectories from stronger teacher models. However, structurally complex questions may remain relatively ea…
- arXiv cs.AIresearchA Survey of Flow Matching in Reinforcement Learning
arXiv:2610.16275v1 Announce Type: cross Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling expressive, multimodal polic…
- arXiv cs.AIagentsSLDBench v2: Active Scaling Law Discovery
arXiv:2610.16297v2 Announce Type: replace-cross Abstract: Scaling laws predict large-model performance from small experiments, but finding a reliable law itself requires costly experiments. SLDBench tests whether languag…
- arXiv cs.AIresearchBehaviorFormer: Discovering Behavioral Patterns via Clusterable Next-Token Prediction
arXiv:2610.16322v1 Announce Type: cross Abstract: Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we extend a next-token p…
- arXiv cs.AIresearchExplicitly Aligned Multi-View Breast Cancer Risk Prediction from Variable-Length Screening Histories
arXiv:2610.16329v1 Announce Type: cross Abstract: Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benefit from both tempo…
- arXiv cs.AIresearchBAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
arXiv:2610.16330v1 Announce Type: cross Abstract: Feed-forward transformer models have driven remarkable progress in 3D vision,yet their quadratic complexity renders them impractical for long video sequences. Streaming 3…
- arXiv cs.AIresearchWorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention
arXiv:2610.16337v1 Announce Type: cross Abstract: Rotary Positional Embedding (RoPE) is widely used to encode relative positions in Transformers. In multi-view settings, however, patch coordinates are defined independent…