AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDon't Skip the Baseline: A Controlled Comparison of Dynamic Expert Skipping in MoEs
arXiv:2610.28369v1 Announce Type: cross Abstract: A growing body of work proposes dynamic expert-skipping methods for Mixture-of-Experts (MoE) models that adjust the number of experts activated per token during inference…
- arXiv cs.AIresearchVisualEvolve: A Skill Self-Evolution Framework for Visual Reasoning
arXiv:2610.28386v1 Announce Type: cross Abstract: Visual tool use enables vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool…
- arXiv cs.AIagentsMAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
arXiv:2610.28397v1 Announce Type: cross Abstract: Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposin…
- arXiv cs.AIresearchThe Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts
arXiv:2610.28407v1 Announce Type: cross Abstract: We present our solution to the AKBC LM-KBC 2026 Shared Task, where we achieved a score of 0.6836 on the official leaderboard, more than double the baseline of 0.2964. Thi…
- arXiv cs.AIagentsRewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time Constraints
arXiv:2610.28409v1 Announce Type: cross Abstract: Large language model agents are often given an inference budget and asked to maximise success within it. A multi-turn agent has to allocate this budget across many enviro…
- arXiv cs.AIresearchBrain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI
arXiv:2610.28411v1 Announce Type: cross Abstract: Deep learning models have become essential tools in medical imaging, yet training them end-to-end for diverse tasks remains challenging due to limited labeled data and co…
- arXiv cs.AIresearchCode2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
arXiv:2610.28416v1 Announce Type: cross Abstract: Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal la…
- arXiv cs.AIresearchDISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets
arXiv:2610.28419v1 Announce Type: cross Abstract: Vision-language trackers (VLTs) accept descriptions intended to assist tracking, but accepting text does not establish that its content changes tracking decisions, partic…
- arXiv cs.AIresearchWorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
arXiv:2610.28423v1 Announce Type: cross Abstract: Generative-prior-based super-resolution (SR) methods leverage implicit knowledge learned from large-scale models to enhance low-resolution inputs. However, such priors ar…
- arXiv cs.AIagentsAfter the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents
arXiv:2610.28425v1 Announce Type: cross Abstract: Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent wi…
- arXiv cs.AIresearchRacer: Hunting GPU Kernel Bugs with Symbolic Equivalence Checking
arXiv:2610.28429v1 Announce Type: cross Abstract: GPU kernels are critical to the performance of today's AI services, yet the same operators are rewritten repeatedly: for each GPU generation, numeric format, serving regi…
- arXiv cs.AIresearchA Digital Twin to Improve Cyber-Social Impact
arXiv:2610.28430v1 Announce Type: cross Abstract: The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has significantly expanded the cyber threat landscape. Traditi…
- arXiv cs.AIresearchPlausible Future, Wrong Choice: Steering World-Action Models toward Intended Future
arXiv:2610.28431v1 Announce Type: cross Abstract: World-Action Models (WAMs) have emerged as a promising paradigm for embodied generalist policies by jointly modeling future world evolution and robot actions across diver…
- arXiv cs.AIresearchEvery Model Leaves a Trace: Multi-Resolution LLM Fingerprinting
arXiv:2610.28434v1 Announce Type: cross Abstract: Large language models leave model-specific traces in their generated text, but it remains unclear how finely these fingerprints can distinguish related models and which s…
- arXiv cs.AIresearchModel- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks
arXiv:2610.28495v1 Announce Type: cross Abstract: Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spik…
- arXiv cs.AIresearchBitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
arXiv:2610.28500v1 Announce Type: cross Abstract: For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memory traffic, and linear-layer execution cost, while…
- arXiv cs.AIresearchECG for laboratory values:A comprehensive physiological and technical analysis
arXiv:2610.28507v1 Announce Type: cross Abstract: Laboratory measurements are essential for clinical decision making but typically require invasive blood sampling. Recent research suggests that ECG recordings may contain…
- arXiv cs.AIresearchVLM-Guided Contact Retargeting and Generative Partner Modeling for Humanoid-Human Interaction
arXiv:2610.28523v1 Announce Type: cross Abstract: Humanoid-human interaction requires robots to operate under severe partial observability: during close physical contact, the human partner is occluded, truncated, or outs…
- arXiv cs.AIresearchBinary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks
arXiv:2610.28543v1 Announce Type: cross Abstract: Discrete diffusion models iteratively denoise a noisy sequence of categorical data such as text, enabling any-order generation with self-correction and in-filling capabil…
- arXiv cs.AIresearchLearning Computational Structure for Sample-Efficient Prediction
arXiv:2610.28555v1 Announce Type: cross Abstract: Statistical learning in high dimensions suffers from the curse of dimensionality. Fortunately, many functions of practical interest are compositionally sparse, meaning th…
- arXiv cs.AIresearchWhen Do LLMs Help with Feature Selection? A Systematic Empirical Study
arXiv:2610.28556v1 Announce Type: cross Abstract: Large language models (LLMs) can leverage semantic feature names alongside summary statistics for tabular feature selection, yet it remains unclear when such information…
- arXiv cs.AIresearchLarge Flow Language Models
arXiv:2610.28559v1 Announce Type: cross Abstract: Continuous flow language models offer a path to parallel generation with tools for control and acceleration unavailable to discrete diffusion, yet effective techniques fo…
- arXiv cs.AIresearchSpatially Informed and Direction Sensitive Representation Learning for Spatial Transcriptomics
arXiv:2610.28579v1 Announce Type: cross Abstract: Cellular states are shaped by both intrinsic gene expression programs and the spatial microenvironment in which cells reside. Spatial transcriptomics makes this context m…
- arXiv cs.AIagentsSceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images
arXiv:2610.28585v1 Announce Type: cross Abstract: Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promis…
- arXiv cs.AIagentsCapable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation
arXiv:2610.28586v1 Announce Type: cross Abstract: Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every token. A natural explanation of where it goes wrong is co…
- arXiv cs.AIresearchTurning TS2Vec into a Foundation Model for Time Series Classification
arXiv:2610.28602v1 Announce Type: cross Abstract: TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew on every dataset: self-superv…
- arXiv cs.AIresearchBenchmarking Arabic Dialects for Math Problems
arXiv:2610.28607v1 Announce Type: cross Abstract: Mathematical reasoning remains underexplored for low-resource languages, including Dialectal Arabic. To bridge this gap, we introduce the DAR-MGSM (Dialectal Arabic Multi…
- arXiv cs.AIresearchMindView: Benchmarking Generative Multi-View Spatial Intelligence
arXiv:2610.28622v1 Announce Type: cross Abstract: Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent…
- arXiv cs.AIresearchIndustrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets
arXiv:2610.28624v1 Announce Type: cross Abstract: Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communic…
- arXiv cs.AIresearchUniWALM: Unified World Action Language Model for Embodied Robot Control
arXiv:2610.28626v1 Announce Type: cross Abstract: Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns vi…
- arXiv cs.AIagentsMechanistic discovery in grain boundary structure and deformation driven by agentic AI
arXiv:2610.28629v2 Announce Type: replace-cross Abstract: Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending these capabi…
- arXiv cs.AIresearchJoints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
arXiv:2610.28632v1 Announce Type: cross Abstract: Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the…
- arXiv cs.AIagentsGibson Env: Real-World Perception for Embodied Agents
arXiv:1808.10654v2 Announce Type: replace Abstract: Developing visual perception models for active agents and sensorimotor control are cumbersome to be done in the physical world, as existing algorithms are too slow to e…
- arXiv cs.AIagentsGenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data
arXiv:2507.21035v4 Announce Type: replace Abstract: Gene expression analysis holds the key to many biomedical discoveries, yet extracting insights from raw transcriptomic data remains challenging due to the complexity of…
- arXiv cs.AIagentsHow Far Are LLMs from Symbolic Planners? An NLP-Based Perspective
arXiv:2508.01300v2 Announce Type: replace Abstract: AI planning provides agents the ability to act autonomously towards achieving a goal in a given environment. Recent advances in Large Language Models (LLMs) have introd…
- arXiv cs.AIresearchLLM-Guided Evolution of Symbolic Acceleration Inequality Families for MILP
arXiv:2508.11850v3 Announce Type: replace Abstract: Integer programming (IP) is central to many combinatorial optimization tasks but remains challenging due to its NP-hard nature. A practical way to improve IP solvers is…
- arXiv cs.AIagentsSingle Agent Robust Deep Reinforcement Learning for Bus Fleet Control
arXiv:2508.20784v3 Announce Type: replace Abstract: Bus bunching remains a challenge for urban transit due to stochastic traffic and passenger demand. Traditional solutions rely on multi-agent reinforcement learning (MAR…
- arXiv cs.AIresearchEMMA: Enhancing Robotic Control Robustness through a Generative Visual Model
arXiv:2509.22407v3 Announce Type: replace Abstract: The generalization of vision-language-action (VLA) models heavily relies on diverse training data. However, acquiring large-scale robot manipulation data across varied…
- arXiv cs.AIagentsVRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems
arXiv:2510.07073v2 Announce Type: replace Abstract: Designing high-performing heuristics for vehicle routing problems (VRPs) is a complex task that requires both intuition and deep domain knowledge. Large language model…
- arXiv cs.AIresearchMitigating Model Merging Conflicts via Knowledge-Aware Task Vector Purification
arXiv:2510.14697v2 Announce Type: replace Abstract: Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods,…
- arXiv cs.AIresearchThe Reward Model Selection Crisis in Personalized Alignment
arXiv:2512.23067v3 Announce Type: replace Abstract: Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference…
- arXiv cs.AIagentsAgents-as-Peers: Bias-Controlled LLM Evaluation as Multi-Agent Peer Assessment
arXiv:2602.02589v2 Announce Type: replace Abstract: Large language model (LLM) evaluation commonly relies on fixed human-authored benchmarks or centralized human/model judges. Fixed benchmarks can age and enter model tra…
- arXiv cs.AIresearchTabular Foundation Models Can Learn Association Rules
arXiv:2602.14622v3 Announce Type: replace Abstract: Association Rule Mining (ARM) is a fundamental task for knowledge discovery in tabular data and is widely used in high-stakes decision-making. Classical ARM methods rel…
- arXiv cs.AIagentsFrom Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation
arXiv:2604.07667v2 Announce Type: replace Abstract: Multi-agent debate improves LLM reasoning, yet agreement is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus…
- arXiv cs.AIagentsNon-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and Remedies
arXiv:2604.23716v5 Announce Type: replace Abstract: Reporting guidance for information-theoretic measures is rarely tested against ground truth. We test one guardrail in two multi-agent reinforcement learning games, a so…
- arXiv cs.AIresearchMental Health AI Safety Claims Must Preserve Temporal Evidence
arXiv:2605.08827v3 Announce Type: replace Abstract: The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dial…
- arXiv cs.AIresearchLearning Transferable Latent User Preferences for Human-Aligned Decision Making
arXiv:2605.12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as reasoning modules in many applications, yet they often struggle to produce human-aligned decisions. Human-aligned…
- arXiv cs.AIresearchBeyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
arXiv:2605.26772v2 Announce Type: replace Abstract: Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control me…
- arXiv cs.AIresearchPReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
arXiv:2605.30803v2 Announce Type: replace Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric asking for a resp…
- arXiv cs.AIresearchThe Shape of Wisdom: How Language Models Converge on an Answer
arXiv:2606.01202v2 Announce Type: replace Abstract: When a language model answers a factual question, where does its internal state go? We asked four open models (Llama-3.1-8B, Qwen2.5-7B, Gemma-2-9B and Llama-3.2-1B) 2,…