AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
arXiv:2606.11260v2 Announce Type: replace-cross Abstract: Humans process rich auditory environments through various cognitive capabilities such as audio perception, audio reasoning and memory. Despite recent progress in…
- arXiv cs.AIagentsTask-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard Detection
arXiv:2606.11889v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) are increasingly used for scene understanding in autonomous driving, but robustness analysis often relies on task-agnostic embedding…
- arXiv cs.AIagentsThreadBench: Benchmarking Realism in Agentic Simulation of Real-world Discussions
arXiv:2606.14715v2 Announce Type: replace-cross Abstract: LLM agents are increasingly used to simulate real-world interactions, but it remains unclear whether simulated behaviors preserve the content patterns and interac…
- arXiv cs.AIresearchLLM Judges Have Dark Current: Stratified Null and Utility Tests for LLM Judge Reliability
arXiv:2606.15610v2 Announce Type: replace-cross Abstract: Passing an exact-clone null gate does not entail passing a matched target-selection utility gate. We call a non-tie preference between exact duplicates dark curre…
- arXiv cs.AIresearchRetrievable Gradients: Continual Post-Training Without Cumulative Weight Drift
arXiv:2606.15734v2 Announce Type: replace-cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, poten…
- arXiv cs.AIagentsBeyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
arXiv:2606.18831v2 Announce Type: replace-cross Abstract: Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over length…
- arXiv cs.AIresearchData-Aware Model Merging in the Essential Subspace for Multi-Task Knowledge Aggregation
arXiv:2606.19164v4 Announce Type: replace-cross Abstract: Model merging enables training-free multi-task learning by aggregating knowledge from models fine-tuned from a shared checkpoint, but their task updates can inter…
- arXiv cs.AIresearchHuman-like autonomy emerges from self-play and a pinch of human data
arXiv:2606.19370v2 Announce Type: replace-cross Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substit…
- arXiv cs.AIagentsScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments
arXiv:2606.20235v2 Announce Type: replace-cross Abstract: Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literat…
- arXiv cs.AIresearchRARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
arXiv:2606.22027v5 Announce Type: replace-cross Abstract: Reinforcement learning for robot manipulation is often bottlenecked by reward design, especially in long-horizon tasks: sparse success rewards provide weak superv…
- arXiv cs.AIresearchOn the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
arXiv:2606.22352v2 Announce Type: replace-cross Abstract: Dictionary learning has long been studied from both optimization and probabilistic perspectives. While formulations with element-wise sparsity regularization (e.g…
- arXiv cs.AIresearchLearning with a Single Rollout via Pass@k Policy Optimization
arXiv:2606.25451v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) typically requires multiple rollouts per prompt to estimate relative credit, incurring substantial sampling cost and exa…
- arXiv cs.AIresearchFrom Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations
arXiv:2606.26277v3 Announce Type: replace-cross Abstract: Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web…
- arXiv cs.AIresearchError-Conditioned Neural Solvers
arXiv:2606.27354v2 Announce Type: replace-cross Abstract: Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task: once trai…
- arXiv cs.AIresearchSPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation
arXiv:2606.27786v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. Ho…
- arXiv cs.AIresearchRoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis
arXiv:2606.28385v2 Announce Type: replace-cross Abstract: Robot world models now generate synthetic manipulation videos, but evaluating them is hard: realistic-looking outputs often violate physical laws, temporal consis…
- arXiv cs.AIresearchWhen AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
arXiv:2606.28438v2 Announce Type: replace-cross Abstract: Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control. We study this ris…
- arXiv cs.AIresearchThe Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
arXiv:2606.28529v3 Announce Type: replace-cross Abstract: Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference t…
- arXiv cs.AIresearchCritical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
arXiv:2606.29898v2 Announce Type: replace-cross Abstract: Real-world evaluation is the gold standard for robot manipulation policies because it tests them against the physical conditions and deployment challenges they ar…
- arXiv cs.AIresearchFederated Learning with Energy-Based Structured Probabilistic Inference
arXiv:2606.30161v2 Announce Type: replace-cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models without sharing their local data. However, heterogeneity in clie…
- arXiv cs.AIresearchReinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
arXiv:2606.32032v2 Announce Type: replace-cross Abstract: Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic…
- arXiv cs.AIresearchOptimal any-angle path planning in static and dynamic environments
arXiv:2607.00065v2 Announce Type: replace-cross Abstract: Any-angle path planning extends traditional graph-based path planning by allowing movement between any pair of vertices, rather than being restricted by predefine…
- arXiv cs.AIresearchEmber: A Kilobyte-State Optimizer for Token Interfaces
arXiv:2607.01455v4 Announce Type: replace-cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them. We show tha…
- arXiv cs.AIresearchBeyond Cultural Persona Bias: Response Geometry as a Measure for Language Models and People
arXiv:2607.02368v4 Announce Type: replace-cross Abstract: Researchers are increasingly prompting language models with cultural personas so that they answer questionnaires as diverse human groups would. However, studies o…
- arXiv cs.AIagentsAutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation
arXiv:2607.02520v2 Announce Type: replace-cross Abstract: Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experim…
- arXiv cs.AIagentsTabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data
arXiv:2607.03926v2 Announce Type: replace-cross Abstract: Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows. Modern gen…
- arXiv cs.AIresearchAuto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding
arXiv:2607.04383v5 Announce Type: replace-cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection (SED)…
- arXiv cs.AIagentsHarnessMDP: Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning
arXiv:2607.05458v3 Announce Type: replace-cross Abstract: The execution harness is a critical component of LLM agents, shaping how the agent interacts with its environment and organizes multi-step execution. Prior work h…
- arXiv cs.AIresearchGraph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion
arXiv:2607.06546v2 Announce Type: replace-cross Abstract: Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures such as graph transfor…
- arXiv cs.AIagentsMulti-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
arXiv:2607.07368v2 Announce Type: replace-cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one…
- arXiv cs.AIresearchEgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
arXiv:2607.08436v2 Announce Type: replace-cross Abstract: Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scenes, and task…
- arXiv cs.AIresearchPhone Segmentation and Recognition through Phonological Activation Mapping
arXiv:2607.09020v2 Announce Type: replace-cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is alread…
- arXiv cs.AIresearchAutomatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works
arXiv:2607.09316v2 Announce Type: replace-cross Abstract: Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-scale literary and hi…
- arXiv cs.AIagentsAn LLM-powered Agentic Recommendation System for Connected TV Content Discovery
arXiv:2607.09988v4 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such…
- arXiv cs.AIresearchComparing Socially-Equitable Renewable Energy Budget Allocation MDP Policies in Mature and Emerging Economies
arXiv:2607.10201v2 Announce Type: replace-cross Abstract: Equitable renewable-energy planning is a sequential decision problem, but the decision variables available to a public planner differ sharply between mature and e…
- arXiv cs.AIresearchScaling Point-in-Time Language Models: Enabling Economic Evaluation of Embeddings
arXiv:2607.11889v3 Announce Type: replace-cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the valid…
- arXiv cs.AIagentsBulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities
arXiv:2607.12723v2 Announce Type: replace-cross Abstract: Container filesystem isolation depends on safely resolving container-controlled paths during privileged host-container interactions. As third-party plugins and ag…
- arXiv cs.AIresearchHALLMARK: How to Diagnose LLM Citation Verifiers and When to Deploy Them
arXiv:2607.18360v2 Announce Type: replace-cross Abstract: GPTZero found 53 NeurIPS 2025 accepted papers with hallucinated citations, and venues now screen submissions with automated reference checkers. Rule- and Large La…
- arXiv cs.AIresearchAudit Before You Update: Recording Artifacts and the Limits of Bounded Model Updates in MIMIC-IV ICU Prediction
arXiv:2607.19020v5 Announce Type: replace-cross Abstract: Clinical prediction models in intensive care degrade as data shift, and regulators such as the FDA ask developers to specify bounded update protocols in advance.…
- arXiv cs.AIagentsChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs
arXiv:2607.19430v3 Announce Type: replace-cross Abstract: AI assistants increasingly work as teams, where one model makes a plan, others search the web, use tools, or read stored information, and another writes the final…
- arXiv cs.AIagentsREGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning
arXiv:2607.19450v4 Announce Type: replace-cross Abstract: Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in larg…
- arXiv cs.AIresearchActivation Steering with Jungian Cognitive Functions
arXiv:2607.20803v3 Announce Type: replace-cross Abstract: Controlling combinations of personality-related tendencies is important for adapting large language models to diverse interaction needs. But successful single-tra…
- arXiv cs.AIagentsDBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents
arXiv:2607.22165v2 Announce Type: replace-cross Abstract: LLM-based database agents show promise, but differences in task scope, testbeds, and success criteria hinder direct comparison. A shared benchmark must also prese…
- arXiv cs.AIresearchConstraint-Aware Influence Estimation in Deep Constrained Learning
arXiv:2607.23388v4 Announce Type: replace-cross Abstract: Constrained learning has been increasingly applied to various domains to ensure explicit feasibility requirements due to fairness, safety, robustness, regularizat…
- arXiv cs.AIagentsMission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric
arXiv:2607.23532v3 Announce Type: replace-cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested environments.…
- arXiv cs.AIresearchThis Is a Good Paper, Right? How Tag Questions Affect Sycophancy Across 106 Language Models
arXiv:2607.23976v2 Announce Type: replace-cross Abstract: Whether a language model agrees with a user depends on how the user asks. We measure this on 106 models with a grid of three wordings and three cues, on 20 person…
- arXiv cs.AIresearchForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models
arXiv:2607.26455v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowled…
- arXiv cs.AIresearchSame Illness, Different Voice: Restating the Patient's Account Narrows Narrative Anchoring in Clinical Language Models
arXiv:2607.27384v2 Announce Type: replace-cross Abstract: Clinical language models are evaluated on vignettes written in a clinician's voice, but patients describe the same illness in their own. We pair 1,000 MedQA cases…
- arXiv cs.AIresearchSpecification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models
arXiv:2607.27964v3 Announce Type: replace-cross Abstract: Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies can lead to deadlock…
- arXiv cs.AIresearchFlux-OPD: On-Policy Distillation with Evolving Contexts
arXiv:2607.28022v2 Announce Type: replace-cross Abstract: Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts de…