AI news archive.
19,854 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchHow Learning Governs Unlearning across the Memorization-Generalization Spectrum
arXiv:2610.08577v1 Announce Type: cross Abstract: While unlearning seeks to negate undesired capabilities acquired through learning, little research has examined how the way models learn shapes their subsequent unlearnin…
- arXiv cs.AIagentsOne for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control
arXiv:2610.08595v1 Announce Type: cross Abstract: Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learning both the compone…
- arXiv cs.AIresearchA Swarm-Coordinated Multi-Robot System for Early Stress Detection in Agricultural Rows Using Multimodal Leaf Sensing
arXiv:2610.08603v1 Announce Type: cross Abstract: Early stress detection in crops is a necessity today to improve efficiency and reduce waste of time, money, and effort. However, most modern techniques, such as hyperspec…
- arXiv cs.AIagentsAgentic RCA for Internet-Scale Services Using Constrained Creativity
arXiv:2610.08622v1 Announce Type: cross Abstract: System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troubleshooting system to…
- arXiv cs.AIresearchEarly Memory Selection for Balanced Adam
arXiv:2610.08624v1 Announce Type: cross Abstract: We propose a method for choosing the shared memory parameter $\beta_1=\beta_2=\beta$ in Adam from a short pilot training. The selected $\beta$ remains fixed during the su…
- arXiv cs.AIresearchFeature Information Dynamics in Diffusion
arXiv:2610.08626v1 Announce Type: cross Abstract: Diffusion models generate data through a continuum of denoising problems, and are widely observed to reveal coarse structure before fine detail. Yet, this intuition is mo…
- arXiv cs.AIresearchHygieneRoboBench: Benchmarking Hygiene-Aware Planning for Household Robots
arXiv:2610.08642v1 Announce Type: cross Abstract: Contact with contaminated objects can spread hazards through a household robot's grippers, tools, and shared surfaces, while new contacts can make an existing plan unsafe…
- arXiv cs.AIagentsA Case Study in Assuring AI-Written Software
arXiv:2610.08651v1 Announce Type: cross Abstract: Software-engineering agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously can produce more cod…
- arXiv cs.AIresearchSelective Transfer of RL Updates for Visual Reasoning
arXiv:2610.08659v1 Announce Type: cross Abstract: Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-based transfer can confl…
- arXiv cs.AIagentsSemantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
arXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks b…
- arXiv cs.AIresearchMemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge
arXiv:2610.08669v1 Announce Type: cross Abstract: On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT)…
- arXiv cs.AIagentsPrincipled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
arXiv:2610.08670v2 Announce Type: replace-cross Abstract: An agent that can say an action is wrong and then take it anyway is a different failure from one that does not know better, and evaluations of stated values canno…
- arXiv cs.AIresearchSecure Speculative Decoding for Large Language Models
arXiv:2610.08678v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to a…
- arXiv cs.AIresearchEgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning
arXiv:2610.08726v1 Announce Type: cross Abstract: Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory ta…
- arXiv cs.AIresearchReinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation
arXiv:2610.08743v1 Announce Type: cross Abstract: Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within a session. We propose Reinforcement Learning with Ca…
- arXiv cs.AIresearchWorldSonus: Bringing Sound to Worlds
arXiv:2610.08760v1 Announce Type: cross Abstract: Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world…
- arXiv cs.AIagentsAdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
arXiv:2610.08773v1 Announce Type: cross Abstract: Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's…
- arXiv cs.AIresearchDepthWorld: 3D World Model for Robot Manipulation
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these…
- arXiv cs.AIresearchIdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
arXiv:2610.08781v1 Announce Type: cross Abstract: Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to pe…
- arXiv cs.AIresearch4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
arXiv:2610.08782v1 Announce Type: cross Abstract: Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from rand…
- arXiv cs.AIresearchWhen Explanations Compete: Policy-Aware Selection Under Uncertainty
arXiv:2410.05479v2 Announce Type: replace Abstract: Uncertainty-aware explanation methods often produce several alternatives for the same prediction. Selecting among them requires a policy for balancing prediction confid…
- arXiv cs.AIagentsDrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search
arXiv:2507.07426v4 Announce Type: replace Abstract: Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their effectiveness remains…
- arXiv cs.AIresearchPuzzleJAX: A Benchmark for Reasoning and Learning
arXiv:2508.16821v2 Announce Type: replace Abstract: We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinforcement learning, and…
- arXiv cs.AIresearchUniverse of Thoughts: A Computational Framework for Creative Reasoning in Large Language Models
arXiv:2511.20471v3 Announce Type: replace Abstract: Recent advances in Large Language Model (LLM) reasoning have improved conventional problem solving, but creative reasoning remains comparatively underexplored. Inspired…
- arXiv cs.AIagentsFRAGMENTA: Efficient End-to-end Fragmentation-based Generative Model with Agentic Tuning for Drug Lead Optimization in Small Data Regime
arXiv:2511.20510v3 Announce Type: replace Abstract: Molecule generation from extremely limited training data is a key challenge in drug discovery. Existing fragment-based methods are more suitable than atom-based approac…
- arXiv cs.AIagentsPrecomputing Multi-Agent Path Replanning Using Temporal Flexibility
arXiv:2601.04884v4 Announce Type: replace Abstract: Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents. So, we need to quickly find a new…
- arXiv cs.AIagentsLearning to Configure Agentic AI Systems
arXiv:2602.11574v5 Announce Type: replace Abstract: Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled tod…
- arXiv cs.AIresearchAlgorithm Selection with Zero Domain Knowledge via Text Embeddings
arXiv:2604.19753v3 Announce Type: replace Abstract: We propose ZeroFolio, a feature-free approach to algorithm selection that uses pretrained text embeddings instead of hand-crafted instance features. It reads the raw in…
- arXiv cs.AIresearchSDFlow: Similarity-Driven Flow Matching for Time Series Generation
arXiv:2605.05736v3 Announce Type: replace Abstract: Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. However, such models ar…
- arXiv cs.AIresearchVon Neumann Networks
arXiv:2605.05780v2 Announce Type: replace Abstract: In the mid-twentieth century, mathematician and polymath John von Neumann created a computational system on an array of cells as a simple model of the human brain, wher…
- arXiv cs.AIresearchXDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
arXiv:2605.05866v2 Announce Type: replace Abstract: Multiphase powder X-ray diffraction (PXRD) analysis remains a fundamental bottleneck in structure identification, as real-world synthesis often produces complex mixture…
- arXiv cs.AIresearchRethinking Adapter Placement: A Dominant Adaptation Module Perspective
arXiv:2605.06183v2 Announce Type: replace Abstract: Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method that places trainable low-rank adapters into frozen pre-trained models. Recent studie…
- arXiv cs.AIresearchReward on Path: Learning Intermediate Supervision Signals for Knowledge Graph Question Answering
arXiv:2605.10791v2 Announce Type: replace Abstract: Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent methods use supervision derived from answer lab…
- arXiv cs.AIresearchWhen Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
arXiv:2605.12922v2 Announce Type: replace Abstract: Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and r…
- arXiv cs.AIagentsEgo2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
arXiv:2605.13335v2 Announce Type: replace Abstract: Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when actions fail. Existi…
- arXiv cs.AIresearchPalette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
arXiv:2605.24154v2 Announce Type: replace Abstract: Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a resu…
- arXiv cs.AIagentsVoluntary Collusion with Secret Tools in Competing LLM Agents
arXiv:2605.27593v2 Announce Type: replace Abstract: Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doi…
- arXiv cs.AIresearchFHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting
arXiv:2605.29695v2 Announce Type: replace Abstract: Approximately 10% of newborns require assistance to initiate breathing at birth, and around 5% need ventilation support. Fetal heart rate (FHR) monitoring plays a cruci…
- arXiv cs.AIagentsCoding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
arXiv:2606.05647v2 Announce Type: replace Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools.…
- arXiv cs.AIagentsSubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
arXiv:2606.05761v3 Announce Type: replace Abstract: Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories over long-term interactions. As these memories grow, they may reinforce one…
- arXiv cs.AIagentsOSGuard: A Benchmark for Safety in Computer-Use Agents
arXiv:2606.15034v3 Announce Type: replace Abstract: Computer-use agents can complete benign user instructions while violating important constraints of the user's environment. We introduce OSGuard, a dual-granularity benc…
- arXiv cs.AIagentsCalibration Is Not Control: Intervention Value for LLM-Agent Oversight
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can differ in whether interve…
- arXiv cs.AIagentsCritic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
arXiv:2607.12397v2 Announce Type: replace Abstract: LLM agents operate in stateful environments, where a single erroneous step can waste limited interaction budget or cause irreversible effects before task failure become…
- arXiv cs.AIresearchBenchmarking the Personalization Capabilities of Large Language Models
arXiv:2607.20471v2 Announce Type: replace Abstract: Personalization is classically a two-party problem: a sender chooses what to say, and a receiver with independent objectives decides whether to act. A salesperson pitch…
- arXiv cs.AIresearchRefusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling
arXiv:2607.20791v2 Announce Type: replace Abstract: Recent advances in truncation-based sampling have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater dive…
- arXiv cs.AIresearchRethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
arXiv:2608.03611v3 Announce Type: replace Abstract: Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete. Existing meth…
- arXiv cs.AIresearchWebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance
arXiv:2608.06704v2 Announce Type: replace Abstract: Delegating a web task involves more than asking a question; it requires transferring a policy: what to verify, how to handle uncertainty, which preferences matter, and…
- arXiv cs.AIresearchPost-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
arXiv:2608.07436v2 Announce Type: replace Abstract: Muon-trained modular-arithmetic transformers can lose accuracy while retaining linearly decodable task information. Adjacent swaps localize five captured unnormalized f…
- arXiv cs.AIagentsUnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
arXiv:2609.09815v2 Announce Type: replace Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocate…
- arXiv cs.AIresearchFast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields
arXiv:2311.18029v2 Announce Type: replace-cross Abstract: The current trend in the literature on Time Series Classification is to develop increasingly accurate algorithms by combining multiple models in ensemble hybrids,…