AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation
arXiv:2610.07460v2 Announce Type: replace-cross Abstract: Inserting objects into existing 3D scenes requires more than selecting a plausible location: the inserted object must also fit local geometry while preserving sem…
- arXiv cs.AIresearchStructure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits
arXiv:2610.07470v1 Announce Type: cross Abstract: Combinatorial Thompson sampling (CTS) draws independent posterior samples for every arm, so its exploration dynamics ignore any relation among arms. We study a minimal ch…
- arXiv cs.AIresearchCan Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance
arXiv:2610.07476v1 Announce Type: cross Abstract: Frontier AI treaties or agreements on limiting computation require external verification; an external auditor must be able to confirm how much computation actually ran an…
- arXiv cs.AIagentsWho Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning
arXiv:2610.07491v1 Announce Type: cross Abstract: When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty should be allocated acr…
- arXiv cs.AIagentsJarvis: A Proactive Speech Agent for Multi-Party Conversations
arXiv:2610.07506v2 Announce Type: replace-cross Abstract: Speech agents are reactive and dyadic: they speak when spoken to, and to one person at a time. We ask what it takes for a speech agent to instead take part in a c…
- arXiv cs.AIresearchHarmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
arXiv:2610.07518v1 Announce Type: cross Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of available evaluations…
- arXiv cs.AIresearchSafeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
arXiv:2610.07532v1 Announce Type: cross Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks including defenses at de…
- arXiv cs.AIagentsDisentangling Models from Personas in Heterogeneous LLM Simulations
arXiv:2610.07535v1 Announce Type: cross Abstract: Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model effects which may domi…
- arXiv cs.AIagentsFoundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network Optimization
arXiv:2610.07550v1 Announce Type: cross Abstract: Random access (RA) is one of the most foundational medium access control (MAC) layer scheduling schemes for handling unpredictable data traffic from multiple terminals. W…
- arXiv cs.AIresearchWhich and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning
arXiv:2610.07553v1 Announce Type: cross Abstract: LoRA fine-tuning adapts small language models (SLMs) to heterogeneous instruction data within a low-rank update subspace, making it vulnerable to three structural problem…
- arXiv cs.AIagentsCheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
arXiv:2610.07557v1 Announce Type: cross Abstract: Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker thr…
- arXiv cs.AIresearchSeeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation
arXiv:2610.07558v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have become a major paradigm for Vision-and-Language Navigation (VLN). However, in safety-critical facilities, invisible risks such as…
- arXiv cs.AIresearchLearning a Mixture of GFlowNets
arXiv:2610.07562v1 Announce Type: cross Abstract: Learning an ensemble of GFlowNets to sample from a discrete target distribution has become a common approach for achieving better state space exploration and convergence…
- arXiv cs.AIresearchComplementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation
arXiv:2610.07565v1 Announce Type: cross Abstract: Complementary Feature Domains (CFD) theory characterizes predictive value as a context-indexed contribution system induced jointly by representations and their realizatio…
- arXiv cs.AIresearchOpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception
arXiv:2610.07569v1 Announce Type: cross Abstract: Dense 3D mapping with semantic understanding is essential for robotic perception in complex environments. Recent 3D Gaussian Splatting-based mapping approaches enable hig…
- arXiv cs.AIresearchMechanistic Interpretability of Atmospheric Rivers in GraphCast
arXiv:2610.07583v1 Announce Type: cross Abstract: While AI weather models now rival operational forecasts, how they represent the atmosphere internally remains an open question: feature attribution reveals which input pa…
- arXiv cs.AIresearchRecurrent Looped Transformer
arXiv:2610.07591v2 Announce Type: replace-cross Abstract: State tracking requires an update at every input, but the depth a Transformer applies to each token is fixed regardless of sequence length. We introduce the Recur…
- arXiv cs.AIresearchModeling Latent Disturbances for Robust Decision-Making in World Models
arXiv:2610.07599v1 Announce Type: cross Abstract: In this paper, we study robust decision-making in the latent space of world models (WMs). Robust optimization is a mathematical framework where, given explicitly specifie…
- arXiv cs.AIresearchEmoception: Selective Affective Layer Fine-Tuning of Video Vision Transformers for Player Arousal Change Recognition From Gameplay Footage
arXiv:2610.07603v1 Announce Type: cross Abstract: This article proposes Selective Affective Layer Fine-Tuning (SALFT), an efficient adaptation framework for Video Vision Transformers in player arousal recognition from ga…
- arXiv cs.AIresearchLinear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution
arXiv:2610.07607v1 Announce Type: cross Abstract: Model-guided directed evolution seeks to identify high-fitness protein variants under limited oracle budgets. Protein language models (PLMs) provide rich representations…
- arXiv cs.AIagentsStateless Language Agents: Scaling Long-Horizon Automated Research
arXiv:2610.07625v1 Announce Type: cross Abstract: Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay growing histories, d…
- arXiv cs.AIresearchMonte Carlo Estimation for KV Cache Eviction
arXiv:2610.07643v2 Announce Type: replace-cross Abstract: Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt? We instead ask which memory will matter while answering?…
- arXiv cs.AIagentsSkillPoison: Progressive Skill Poisoning via Successful Experiences
arXiv:2610.07645v1 Announce Type: cross Abstract: Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by in…
- arXiv cs.AIresearchSMART: Zero-Shot Sim-to-Real Articulated Object Manipulation via Large-Scale Synthetic Pretraining
arXiv:2610.07652v1 Announce Type: cross Abstract: The ability to interact with articulated objects is essential for embodied intelligent systems, but collecting large-scale real-world demonstrations for these interaction…
- arXiv cs.AIresearchDoes On-Policy Distillation for Safety Pose Backdoor Risks?
arXiv:2610.07654v1 Announce Type: cross Abstract: On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Recent studies further ex…
- arXiv cs.AIagentsJoint Workflow and Prompt Optimization for User Behavior Simulation
arXiv:2610.07663v1 Announce Type: cross Abstract: User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users. It supp…
- arXiv cs.AIresearchSENSE: State-aware Emotion Navigation Storytelling Engine
arXiv:2610.07666v1 Announce Type: cross Abstract: This paper presents SENSE, a state-aware framework for generating playable branching visual novels with multi-track emotional navigation. Integrating a state-based narrat…
- arXiv cs.AIresearchCACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency
arXiv:2610.07668v1 Announce Type: cross Abstract: Modern cache replacement designs saturate because they operate within fixed representational structures, hand-crafted and heuristic based feature-engineered predictors, o…
- arXiv cs.AIagentsEvaluating human-AI workflows for field research in viticulture
arXiv:2610.07669v1 Announce Type: cross Abstract: We assessed the value of two live human-AI interactions in a precision disease control project in California vineyards. The project tested whether 2021-2024 commercial sc…
- arXiv cs.AIresearchExact-Solution Volume and Length Generalization in Transformers
arXiv:2610.07676v1 Announce Type: cross Abstract: Research on transformer expressivity shows whether a transformer is capable of solving a given task, but gives little indication of whether the solution, if learned, is g…
- arXiv cs.AIresearchEigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors
arXiv:2610.07681v2 Announce Type: replace-cross Abstract: Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinf…
- arXiv cs.AIresearchDisentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
arXiv:2610.07684v1 Announce Type: cross Abstract: Personalized image generation aims to synthesize text-driven images conditioned on reference images, while mainly casting the generation as image customization for foregr…
- arXiv cs.AIresearchWhat Frame-Level Labels Can and Cannot Do for Small-UAV Point Detection in Thermal Video
arXiv:2610.07705v1 Announce Type: cross Abstract: The growing use of unmanned aerial vehicles (UAVs) has increased the importance of image-based UAV detection. Learning-based detectors are trained on imagery and annotati…
- arXiv cs.AIresearchWASD: Wasserstein-based Knowledge Distillation for Large Language Models
arXiv:2610.07706v1 Announce Type: cross Abstract: Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and memory costs at infer…
- arXiv cs.AIresearchSanSi: A Looped Typed Decision Model for System 1.5 Thinking
arXiv:2610.07730v2 Announce Type: replace-cross Abstract: Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a single forwa…
- arXiv cs.AIresearchLearning to Retrieve via Reinforcement Learning in Embedding Space
arXiv:2610.07731v1 Announce Type: cross Abstract: Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval metrics or downstream…
- arXiv cs.AIresearchCleave: Scaling Tensor Program Optimization via Decoupled Algebraic Search and Operator Scheduling
arXiv:2610.07742v1 Announce Type: cross Abstract: Optimized kernels such as FlashAttention and FlashDecoding are crucial for accelerating today's large models. Most of them are handwritten by experts because existing ML…
- arXiv cs.AIagentsFrom Evidence to Action: How Tool-Using Agents Fail
arXiv:2610.07753v1 Announce Type: cross Abstract: Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand…
- arXiv cs.AIresearchLater Is Better: Token Reduction for ViTs Under Distribution Shift
arXiv:2610.07758v1 Announce Type: cross Abstract: Training-free token reduction accelerates vision transformers by removing redundant tokens across layers, recovering most of the original accuracy at a fraction of the co…
- arXiv cs.AIresearchContrastive Learning for Aspect Representation towards Explainable Recommendation
arXiv:2610.07761v1 Announce Type: cross Abstract: In this work, we propose a novel recommendation model, CLARER (Contrastive Learning for Aspect Representation towards Explainable Recommendation) that integrates aspect f…
- arXiv cs.AIresearchNo Transformer Beats Six Covariates: Long-Horizon Prediction of Depressive Symptoms from Childhood Essays
arXiv:2610.07764v1 Announce Type: cross Abstract: Natural language processing (NLP) models can detect depression-related language in text written near the time symptoms are measured, but whether pretrained transformers c…
- arXiv cs.AIresearchTowards One-for-All Foundation Model for Attributed Graph Clustering
arXiv:2610.07778v1 Announce Type: cross Abstract: Attributed graph clustering aims to discover node groups by jointly exploiting node attributes and graph topology, yet its unsupervised nature makes model selection and a…
- arXiv cs.AIagentsServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?
arXiv:2610.07792v1 Announce Type: cross Abstract: Large language model agents are increasingly deployed to perform complex tasks in real-world environments. However, the knowledge required for correct behavior in these e…
- arXiv cs.AIagentsThe Geometry of Empowerment
arXiv:2610.07796v2 Announce Type: replace-cross Abstract: Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity, the connect…
- arXiv cs.AIresearchNovice Reliance Calibration in AI-Assisted Decision Making: The Role of Explanations and Self-Assessment
arXiv:2610.07800v1 Announce Type: cross Abstract: Artificial Intelligence (AI) tools are widely used to support decision making in tasks and domains where no immediate performance feedback is available. In these settings…
- arXiv cs.AIagentsOne Step at a Time: Trading LLM Autonomy for Process Predictability
arXiv:2610.07817v1 Announce Type: cross Abstract: Organizations automating operational processes need more than a correct outcome: they need to predict how a process will run, know which one actually ran, and inspect it…
- arXiv cs.AIagentsHarness Engineering for Software Engineering via Modular Executable Dev-Primitives
arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain…
- arXiv cs.AIresearchDynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language Models
arXiv:2610.07848v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large language models to downstream tasks. However, most existing PEFT methods rely on…
- arXiv cs.AIagentsA self-learning scientific agent for X-ray diffraction
arXiv:2610.07862v1 Announce Type: cross Abstract: A central challenge for scientific agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-lear…
- arXiv cs.AIagentsReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessio…