AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsHarnessing LLM Agents with Skill Programs
arXiv:2605.17734v2 Announce Type: replace Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However…
- arXiv cs.AIagentsDemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback
arXiv:2605.24539v2 Announce Type: replace Abstract: Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon task…
- arXiv cs.AIresearchBoosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
arXiv:2605.27023v5 Announce Type: replace Abstract: Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are…
- arXiv cs.AIagentsKLineage: Recovering the Missing When of Kernel Optimization by Deoptimizing Experts
arXiv:2605.28213v2 Announce Type: replace Abstract: LLM-based agents are increasingly used to generate GPU kernels, but they often struggle to determine when an optimization is sound because its required code state and d…
- arXiv cs.AIresearchDiversifying RLVR Rollouts via First-Token Exploration
arXiv:2605.28295v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) trains reasoning models without labeled trajectories, using groups of verifier-scored rollouts to explore alternat…
- arXiv cs.AIagentsDeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability
arXiv:2605.29522v2 Announce Type: replace Abstract: As scientific literature grows rapidly and research increasingly involves AI agents, automated survey generation has become a key capability for both agents and human r…
- arXiv cs.AIagentsSoftSkill: Behavioral Compression for Contextual Adaptation
arXiv:2606.20333v2 Announce Type: replace Abstract: Natural-language skills let agents reuse task knowledge, yet deploying a long Markdown document makes the model interpret that knowledge anew on every call. We ask whet…
- arXiv cs.AIagentsThe Hitchhiker's Guide to Agentic AI: From Foundations to Systems
arXiv:2606.24937v3 Announce Type: replace Abstract: The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems, covering the full stack from first principles to pr…
- arXiv cs.AIresearchRater State Bias in RLHF Preference Data: An Audit Framework
arXiv:2607.16195v3 Announce Type: replace Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but the…
- arXiv cs.AIresearchJUMP: Efficient Membership Inference on Fine-Tuned Diffusion Language Models
arXiv:2607.16207v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) test whether a candidate example was used to train a language model. Existing attacks on fine-tuned discrete diffusion language mode…
- arXiv cs.AIagentsWhen Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops
arXiv:2607.25152v2 Announce Type: replace Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold:…
- arXiv cs.AIresearchBelief-Guided Decision Making with Uncertainty Gating in the Game of Go
arXiv:2607.26946v2 Announce Type: replace Abstract: Recent advancements in Computer Go, driven by AlphaZero and MuZero, rely heavily on Monte Carlo Tree Search (MCTS) to correct the errors of the neural network policy. W…
- arXiv cs.AIagentsXBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
arXiv:2608.11676v2 Announce Type: replace Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning p…
- arXiv cs.AIresearchDecode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
arXiv:2608.12385v3 Announce Type: replace Abstract: As large language models serve ever more requests, cumulative inference cost is growing relative to the one-time cost of training. In typical serving, prompt prefill ru…
- arXiv cs.AIresearchFrom Answers to Policies: Efficient In-Context Learning System through Emulating Expert Investigation
arXiv:2608.16831v2 Announce Type: replace Abstract: Pretrained large language models offer a practical foundation for learning useful behavior from few task-specific examples. We argue that current prompt and context opt…
- arXiv cs.AIresearchRethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning
arXiv:2608.19966v2 Announce Type: replace Abstract: Multivariate time series forecasting (MTSF) is a fundamental task in many real world applications. Existing patch based forecasting methods generally fall into three ca…
- arXiv cs.AIresearchSolving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games
arXiv:2608.24986v2 Announce Type: replace Abstract: Robust POMDPs (RPOMDPs) generalize classical POMDPs to the setting where exact transition probabilities are not known -- rather, they are only known to belong to some u…
- arXiv cs.AIagentsBenevolent Bias in Multi-Turn Human-Agent Dialogue
arXiv:2608.29206v2 Announce Type: replace Abstract: Bias in human-agent interaction can manifest not only through hostile language but also as benevolent bias, whereby unequal treatment hides behind a warm, positive tone…
- arXiv cs.AIresearchVision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
arXiv:2609.00355v3 Announce Type: replace Abstract: Speculative decoding accelerates generation without changing its output, but on vision-language models (VLMs) a self-reinforcing cycle holds it back. Because an autoreg…
- arXiv cs.AIagentsSRPO: Setwise Relative Policy Optimization for Multi-Agent Systems
arXiv:2609.08452v2 Announce Type: replace Abstract: Multi-agent systems enable complex reasoning and tool use by coordinating agents that divide roles and refine candidate solutions. Existing methods typically update ind…
- arXiv cs.AIagentsAgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
arXiv:2609.08572v2 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance depends on the pro…
- arXiv cs.AIagentsRoot-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
arXiv:2609.13463v2 Announce Type: replace Abstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it t…
- arXiv cs.AIresearchHow Should Reasoning Be Organized in a Transformer's Latent Space?
arXiv:2609.13747v2 Announce Type: replace Abstract: Continuous reasoning has emerged as a promising way to improve reasoning in large language models (LLMs). Yet we still lack a clear principle for deciding what a latent…
- arXiv cs.AIresearchOn the Approximation and Convergence of Distributional Policy Gradient Algorithms for Risk-Sensitive Reinforcement Learning
arXiv:2405.14749v3 Announce Type: replace-cross Abstract: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn…
- arXiv cs.AIresearchBadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
arXiv:2406.00083v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant information from external knowledge bases to provide more accura…
- arXiv cs.AIresearchRecKG: Knowledge Graph for Recommender Systems
arXiv:2501.03598v2 Announce Type: replace-cross Abstract: Knowledge graphs have proven successful in integrating heterogeneous data across various domains. However, there remains a noticeable dearth of research on their…
- arXiv cs.AIresearchCausal pieces: analysing and improving spiking neural networks piece by piece
arXiv:2504.14015v2 Announce Type: replace-cross Abstract: We introduce "causal pieces", a novel concept for analysing spiking neural networks (SNNs), inspired by "linear pieces" used to study expressivity and trainabilit…
- arXiv cs.AIresearchMoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing
arXiv:2506.01004v3 Announce Type: replace-cross Abstract: Unlike traditional video editing or inpainting, video semantic mixing fuses a reference concept with a moving target entity to produce a hybrid while preserving t…
- arXiv cs.AIresearchGondola: Grounded Vision Language Planning for Robotic Manipulation
arXiv:2506.11261v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have shown promising progress in robotic manipulation. However, directly mapping visual observations and language instructions…
- arXiv cs.AIagentsMeta-SecAlign: Training LLMs against Prompt Injection for Robust Agents
arXiv:2507.02735v4 Announce Type: replace-cross Abstract: Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to AI agents. By…
- arXiv cs.AIresearchLearning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning
arXiv:2507.12612v5 Announce Type: replace-cross Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks. In practi…
- arXiv cs.AIresearchLLM Serving Optimization with Variable Prefill and Decode Lengths
arXiv:2508.06133v5 Announce Type: replace-cross Abstract: We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and re…
- arXiv cs.AIresearchMitigating Cross-Image Information Leakage in Multi-Image Understanding with Large Vision-Language Models
arXiv:2508.13744v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) exhibit strong performance on single-image tasks. However, their performance degrades significantly when handling multi-image…
- arXiv cs.AIresearchGeometrically Constrained and Token-Based Probabilistic Spatial Transformers
arXiv:2509.11218v3 Announce Type: replace-cross Abstract: Spatial transformations such as rotation and scale obscure the morphological cues needed for accurate image classification. Careful consideration is required for…
- arXiv cs.AIresearchAdversarial Defense in Cybersecurity: A Systematic Review of GANs for Threat Detection and Mitigation
arXiv:2509.20411v3 Announce Type: replace-cross Abstract: Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act as both powerful attac…
- arXiv cs.AIresearchHybrid Approach for Enhancing Lesion Segmentation in Fundus Images
arXiv:2509.25549v3 Announce Type: replace-cross Abstract: Choroidal nevi are common benign pigmented lesions in the eye, with a small risk of transforming into melanoma. Early detection is critical to improving survival…
- arXiv cs.AIresearchCPATTA: Conformal Supervision Allocation For Active Test-Time Adaptation
arXiv:2509.25692v2 Announce Type: replace-cross Abstract: Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use…
- arXiv cs.AIresearchBeyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
arXiv:2510.22752v2 Announce Type: replace-cross Abstract: In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous t…
- arXiv cs.AIresearchEvidence-Guided Schema Normalization for Temporal Tabular Reasoning
arXiv:2512.00329v2 Announce Type: replace-cross Abstract: Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task as automated knowled…
- arXiv cs.AIresearchTraining-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation
arXiv:2512.18991v3 Announce Type: replace-cross Abstract: Dominant paradigms for 4D LiDAR panoptic segmentation are usually required to train deep neural networks with large superimposed point clouds or design dedicated…
- arXiv cs.AIresearchData-Free Pruning of Self-Attention Layers in LLMs
arXiv:2512.20636v2 Announce Type: replace-cross Abstract: Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppression Hypothesis: du…
- arXiv cs.AIresearchAsymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling
arXiv:2601.08777v2 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) to serve users with heterogeneous and potentially conflicting preferences is a central challenge for personalized and trustw…
- arXiv cs.AIresearchUncertainty-aware Causal Decision Making via Effect Bound Decomposition
arXiv:2601.22736v3 Announce Type: replace-cross Abstract: Causal inference from observational data can provide strong evidence for finding the best action in a decision-making scenario without having to perform expensive…
- arXiv cs.AIresearchPhaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science
arXiv:2602.03915v2 Announce Type: replace-cross Abstract: Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned,…
- arXiv cs.AIresearchFrom Concept Erasure to Style Purification: Contrastive Eigenbases for Artist Style Protection
arXiv:2602.08059v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can reproduce specific artists visual styles at extremely low cost, raising copyright and deployment safety concerns about unauthor…
- arXiv cs.AIagentsEvaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
arXiv:2602.11988v3 Announce Type: replace-cross Abstract: A widespread practice in software development is to tailor coding agents to repositories using context files, such as AGENTS.md. Although this practice is strongl…
- arXiv cs.AIresearchOn Calibration of Large Language Models: From Response To Capability
arXiv:2602.13540v2 Announce Type: replace-cross Abstract: Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on response-level confi…
- arXiv cs.AIresearchRobo-Saber: Generating and Simulating Virtual Reality Players
arXiv:2602.18319v2 Announce Type: replace-cross Abstract: We present the first motion generation system for playtesting virtual reality (VR) games. Our player model generates VR headset and handheld controller movements…
- arXiv cs.AIagentsAgentic AI for Scalable and Robust Optical Systems Control
arXiv:2602.20144v2 Announce Type: replace-cross Abstract: We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interp…
- arXiv cs.AIresearchCOMiT: Learning Structured Visual Tokens through Sequential Communication
arXiv:2602.20731v2 Announce Type: replace-cross Abstract: Discrete image tokenizers provide a sequential interface for vision and multimodal models, but are typically optimized for reconstruction or compression and there…