AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchContactExplorer: Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipulation
arXiv:2603.10971v4 Announce Type: replace-cross Abstract: Reinforcement learning explores effectively in domains such as Atari games, navigation, and locomotion, where novelty over states or dynamics is a sufficient sign…
- arXiv cs.AIresearchAltered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy
arXiv:2603.12717v3 Announce Type: replace-cross Abstract: Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are designed to reason in t…
- arXiv cs.AIresearchTabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins
arXiv:2603.15481v3 Announce Type: replace-cross Abstract: Data-free knowledge distillation enables model compression without original training data, critical for privacy-sensitive tabular domains. However, existing metho…
- arXiv cs.AIresearchPure and physics-guided deep learning approaches for spatio-temporal groundwater level prediction
arXiv:2603.25779v2 Announce Type: replace-cross Abstract: Groundwater represents a key element of the water cycle, yet it exhibits complex and context-dependent relationships that make its modeling challenging. Theory-ba…
- arXiv cs.AIresearchScreening Is Enough
arXiv:2604.01178v4 Announce Type: replace-cross Abstract: We call query--key relevance absolute when its values lie on a fixed bounded scale, depend on neither competing keys nor sequence length, require no sequence-leng…
- arXiv cs.AIresearchSuppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs
arXiv:2604.03114v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy changes. Conventiona…
- arXiv cs.AIresearchRevisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
arXiv:2604.08880v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation…
- arXiv cs.AIresearchQuery Lower Bounds for Diffusion Sampling
arXiv:2604.10857v2 Announce Type: replace-cross Abstract: Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by minimizing the…
- arXiv cs.AIagentsCollective Opinion Dynamics in Structured LLM Populations
arXiv:2604.11312v3 Announce Type: replace-cross Abstract: Large Language Models are increasingly deployed as interacting agents in settings such as online platforms, recommendation systems, and multi-agent applications.…
- arXiv cs.AIresearchPAC-CF: Calibrating Irreversible Frontier Pruning in LLM-Guided Search
arXiv:2604.14345v5 Announce Type: replace-cross Abstract: LLM-guided search explores multiple candidate trajectories, but at substantial test-time cost. Pruning low-scoring frontier candidates can control this cost, yet…
- arXiv cs.AIresearchAmortized Optimal Transport from Sliced Potentials
arXiv:2604.15114v2 Announce Type: replace-cross Abstract: We propose a novel amortized optimization method for predicting optimal transport (OT) plans across multiple pairs of measures by leveraging Kantorovich potential…
- arXiv cs.AIresearchReplay-buffer engineering for noise-aware quantum circuit optimization
arXiv:2604.21863v2 Announce Type: replace-cross Abstract: Deep reinforcement learning for quantum circuit optimization faces three bottlenecks: replay buffers that overlook temporal difference (TD) target reliability, cu…
- arXiv cs.AIresearchUtility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs
arXiv:2604.22893v2 Announce Type: replace-cross Abstract: Traditional ``row-count $\times$ quality coefficient'' approaches fail to capture the nonlinear utility of data for Large Language Model (LLM) capabilities. We pr…
- arXiv cs.AIresearchUnderstanding Scattered Forest Search: A Version-Space Perspective on Multi-Turn Program Correction
arXiv:2604.23989v3 Announce Type: replace-cross Abstract: In multi-turn program correction, the state-of-the-art method Scattered Forest Search (SFS) has been proposed, employing Monte Carlo Tree Search (MCTS) with caref…
- arXiv cs.AIresearchSingle-turn emergency psychiatric triage across 15 frontier AI chatbots
arXiv:2604.25415v3 Announce Type: replace-cross Abstract: People increasingly turn to general-purpose AI chatbots for advice about emotional and mental health problems, but the ability of these systems to recognize and a…
- arXiv cs.AIresearchGRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
arXiv:2605.01688v2 Announce Type: replace-cross Abstract: Long-horizon memory systems increasingly improve how evidence is stored and retrieved, yet the generator must still reason over fragments whose cross-session rela…
- arXiv cs.AIagentsTrojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. The Trojan Hippo attack…
- arXiv cs.AIresearchCumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inherit a task that earlier…
- arXiv cs.AIresearchNoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
arXiv:2605.08144v2 Announce Type: replace-cross Abstract: Training a diffusion model involves two sources of randomness for each data sample: the timestep and the Gaussian noise realization. The timestep has been studied…
- arXiv cs.AIresearchPowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
arXiv:2605.10335v2 Announce Type: replace-cross Abstract: Adaptive optimizers such as Adam are standard for training Transformers, but storing gradient first and second moments incurs substantial memory overhead. We intr…
- arXiv cs.AIresearchPRISM: A Geometric Risk Bound for Decomposing Drift into Scale, Shape, and Head
arXiv:2605.11608v2 Announce Type: replace-cross Abstract: A single base LLM now comes with dozens of post-training variants, quantized, LoRA-adapted, or distilled, and each has to be checked before release. Existing eval…
- arXiv cs.AIagentsMissing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
arXiv:2605.12070v3 Announce Type: replace-cross Abstract: Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it a…
- arXiv cs.AIresearchGenerative Support Realignment for Cross-Domain Offline Reinforcement Learning
arXiv:2605.13054v2 Announce Type: replace-cross Abstract: Cross-domain offline reinforcement learning learns a target policy from pre-collected source and target datasets with different dynamics. When target data are sca…
- arXiv cs.AIresearchFactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
arXiv:2605.14854v4 Announce Type: replace-cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This ambiguity i…
- arXiv cs.AIresearchEdge-AI-Driven Learning-to-Rank for Decentralized Task Allocation in Circular Smart Manufacturing
arXiv:2605.16433v4 Announce Type: replace-cross Abstract: Task allocation in smart manufacturing systems must operate under decentralized decision-making, dynamic workloads, and shared-resource constraints. In circular m…
- arXiv cs.AIresearchObservation-Aligned Mask Priors for Learning Physical Fields from Authentic Occlusions
arXiv:2605.16818v2 Announce Type: replace-cross Abstract: Learning physical fields directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and often missing not…
- arXiv cs.AIagentsAgentic Graph Retrieval-Augmented Generation for Auditable Commercial Registry Analysis
arXiv:2605.18770v3 Announce Type: replace-cross Abstract: Public commercial registries are formally open, yet their practical analysis remains difficult because relevant facts are scattered across millions of records tha…
- arXiv cs.AIagentsTwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
arXiv:2605.18859v5 Announce Type: replace-cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers…
- arXiv cs.AIresearchAccelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
arXiv:2605.20624v2 Announce Type: replace-cross Abstract: Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial late…
- arXiv cs.AIresearchEvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
arXiv:2605.21862v3 Announce Type: replace-cross Abstract: Chunked vision-language-action (VLA) policies generate multi-step actions from one observation and typically re-observe after executing the action chunk. Earlier…
- arXiv cs.AIresearchDecomposing and Measuring Evaluation Awareness
arXiv:2605.23055v3 Announce Type: replace-cross Abstract: Frontier language models sometimes recognize that they are under evaluation and adjust their behavior which can undermine validity of benchmark results. Yet the f…
- arXiv cs.AIresearchScalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
arXiv:2605.23194v2 Announce Type: replace-cross Abstract: Fast and reliable optimal power flow (OPF) approximation is important for power system operation, yet heterogeneous OPF graph models are often evaluated either wi…
- arXiv cs.AIresearchAdaptive Mass-Segmented KV Compression for Long-Context Reasoning
arXiv:2605.23200v2 Announce Type: replace-cross Abstract: The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting token…
- arXiv cs.AIresearchAdvantageFlow: Regularized Advantage-Weighted RL in Flow Models
arXiv:2605.26013v2 Announce Type: replace-cross Abstract: We present AdvantageFlow, a forward-process reinforcement learning (RL) algorithm for rectified flow models. The algorithm minimizes an advantage-weighted predict…
- arXiv cs.AIagentsLearning to Assign Prediction Tasks to Agents with Capacity Constraints
arXiv:2605.27999v2 Announce Type: replace-cross Abstract: We address the problem of learning to assign prediction tasks to one agent from a set of available agents, including human decision-makers and AI models. We focus…
- arXiv cs.AIresearchEfficient Pre-Training of LLMs through Truncated SVD Representations
arXiv:2605.28573v2 Announce Type: replace-cross Abstract: LLM pretraining is extremely costly; therefore, parameter-efficient LLM architectures have recently emerged as a compelling research direction. One such promising…
- arXiv cs.AIagentsDo Proactive Agents Need an LLM to Decide When to Act?
arXiv:2605.30152v2 Announce Type: replace-cross Abstract: Proactive assistants continuously decide when to intervene and what context should support the intervention. Large language model (LLM) pipelines repeatedly inter…
- arXiv cs.AIresearchReasoning with Sampling: Cutting at Decision Points
arXiv:2605.30327v2 Announce Type: replace-cross Abstract: Frontier reasoning models are produced by post-training base language models with reinforcement learning. Recent work has challenged this by showing that sampling…
- arXiv cs.AIresearchTwo-Fidelity Best-Action Identification for Stochastic Minimax Tree
arXiv:2606.01708v2 Announce Type: replace-cross Abstract: We study fixed-confidence best-action identification (BAI) in stochastic minimax trees. This problem is increasingly relevant in modern AI planning, where deep mi…
- arXiv cs.AIresearchRobotValues: Evaluating Household Robots When Human Values Conflict
arXiv:2606.03312v2 Announce Type: replace-cross Abstract: While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations where robots are expected…
- arXiv cs.AIresearchReproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
arXiv:2606.04923v3 Announce Type: replace-cross Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models may exploit…
- arXiv cs.AIagentsHANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
arXiv:2606.06493v4 Announce Type: replace-cross Abstract: Humanoid loco-manipulation benefits from one controller to coordinate locomotion, arm movements, and fall recovery. These behaviors are difficult to learn togethe…
- arXiv cs.AIresearchFisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning
arXiv:2606.10196v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning often selects trainable parameters before adaptation using architectural heuristics, without accounting for their varying importan…
- arXiv cs.AIresearchUPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation
arXiv:2606.10466v4 Announce Type: replace-cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverag…
- arXiv cs.AIresearchActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3
arXiv:2606.16996v2 Announce Type: replace-cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segment…
- arXiv cs.AIagentsSkill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
arXiv:2606.18837v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing method…
- arXiv cs.AIresearchTemporal Self-Imitation Learning
arXiv:2606.19752v3 Announce Type: replace-cross Abstract: Long-horizon policies trained with reinforcement learning can still achieve high return through inefficient interactions, while rare efficient behaviors discovere…
- arXiv cs.AIagentsIs Agent Code Less Maintainable Than Human Code?
arXiv:2606.21804v2 Announce Type: replace-cross Abstract: Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agents have demonstrated…
- arXiv cs.AIresearchLow-power analogue neural networks with trainable nonlinear connections for continuous control
arXiv:2606.23742v2 Announce Type: replace-cross Abstract: Physical neural networks promise low-power machine learning by computing directly with analogue device physics, but most architectures force nonlinear device resp…
- arXiv cs.AIresearchDoes Anthropomorphic Language Impact Public Perceptions of AI?
arXiv:2606.29121v2 Announce Type: replace-cross Abstract: Public discourse about artificial intelligence (AI) often uses anthropomorphic language: language that attributes human capabilities and characteristics to AI sys…