AI news archive.
19,854 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrom Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost
arXiv:2609.21117v1 Announce Type: cross Abstract: AI productivity is often measured by task completion time, economic value, or improvements in outcome quality. However, these measures usually treat collaboration as a bl…
- arXiv cs.AIresearchThe Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators
arXiv:2609.21133v1 Announce Type: cross Abstract: SQL has been augmented with AI operators, enabling modern data analytics platforms to derive insights from both structured and unstructured data. We observe that while cu…
- arXiv cs.AIresearchEnSol: an environment-aware graph neural network for molecular solubility prediction
arXiv:2609.21151v1 Announce Type: cross Abstract: Molecular solubility directly affects key aspects of molecular development such as reaction feasibility, formulation performance, separation efficiency, and solvent selec…
- arXiv cs.AIagentsSWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
arXiv:2609.21190v2 Announce Type: replace-cross Abstract: Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check correctness with…
- arXiv cs.AIresearchVisual Navigation Transformer with Pose Attention
arXiv:2609.21212v1 Announce Type: cross Abstract: Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when it was seen, making i…
- arXiv cs.AIresearchFewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies
arXiv:2609.21216v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies based on flow matching generate action chunks through repeated evaluations of an action expert. Increasing the number of integration…
- arXiv cs.AIresearchHallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency
arXiv:2609.21227v1 Announce Type: cross Abstract: Factual hallucination is commonly defined by incorrect factual outputs. We study a paraphrase-induced hallucination setting, where a model answers a factual question corr…
- arXiv cs.AIresearchFOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models
arXiv:2609.21228v1 Announce Type: cross Abstract: Vision-language-action (VLA) models built on pretrained vision-language models have demonstrated strong performance across diverse robotic manipulation tasks. However, VL…
- arXiv cs.AIresearchKnowDemo: Knowledge-Guided Robot Demonstration Generation from Human Videos
arXiv:2609.21229v1 Announce Type: cross Abstract: Learning robot manipulation policies typically requires substantial demonstration data, which are costly to collect on real robots. Recent methods generate robot demonstr…
- arXiv cs.AIresearchVLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models
arXiv:2609.21246v1 Announce Type: cross Abstract: Vision-language-action (VLA) models map visual observations and natural-language instructions to robotic actions, but distribution shifts can compromise their reliability…
- arXiv cs.AIagentsVerify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale
arXiv:2609.21257v1 Announce Type: cross Abstract: Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a…
- arXiv cs.AIresearchBeyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering
arXiv:2609.21276v1 Announce Type: cross Abstract: In automated Printed Circuit Board Assembly (PCBA) inspection, standards-guided decisions require systems to jointly reason over fine-grained visual cues, component seman…
- arXiv cs.AIagentsAuthorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution
arXiv:2609.21284v1 Announce Type: cross Abstract: Long-running AI agents outlive initiating processes through credentials, delegated tasks, queues, callbacks, reservations, and provider-side operations. Cancellation, pro…
- arXiv cs.AIresearchDeep Reinforcement Learning with Buffered Quantile Objectives
arXiv:2609.21327v1 Announce Type: cross Abstract: Quantile-based reinforcement learning provides an interpretable approach to risk-sensitive decision-making by optimizing a prescribed quantile of the cumulative-return di…
- arXiv cs.AIresearchCo-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection
arXiv:2609.21334v1 Announce Type: cross Abstract: Effective evaluation of zero-day jamming detectors requires robust adversarial models. However, existing attack models often assume prior knowledge of the target receiver…
- arXiv cs.AIresearchCESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices
arXiv:2609.21344v1 Announce Type: cross Abstract: For Internet of Things (IoT) devices, a secure algorithm alone is not enough: an attacker with physical access can attack the implementation directly, and its flaws are h…
- arXiv cs.AIagentsFrom Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers
arXiv:2609.21349v1 Announce Type: cross Abstract: Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existing in-context learnin…
- arXiv cs.AIresearchKnowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting
arXiv:2609.21381v1 Announce Type: cross Abstract: We investigate whether coupling a time-series foundation model to hydraulic project knowledge improves surrogate forecasting of HEC-RAS water-surface elevation (WSE). We…
- arXiv cs.AIagentsAgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents
arXiv:2609.21386v1 Announce Type: cross Abstract: Comprehensive video understanding is crucial for advancing artificial intelligence toward the intricate dynamics of the physical world. While recent advances in Multimoda…
- arXiv cs.AIresearchConsistent Relexicalization of Clinical Documents using Graph-Based Approach
arXiv:2609.21387v1 Announce Type: cross Abstract: Relexicalization is a pivotal technique in clinical NLP, as it facilitates robust masking of sensitive information while synthesizing datasets that retain high-fidelity,…
- arXiv cs.AIresearchWS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field
arXiv:2609.21391v1 Announce Type: cross Abstract: Neural Radiance Fields (NeRF) have attracted extensive attention in recent years due to their strong capability for high-quality 3D reconstruction and novel view synthesi…
- arXiv cs.AIresearchTalking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue
arXiv:2609.21401v1 Announce Type: cross Abstract: Conversational AI systems produce fluent, socially appropriate responses, yet whether they participate in cooperative communication or merely simulate its surface forms r…
- arXiv cs.AIresearchThink Locally, Refine Globally for Memory-Efficient 3D Reconstruction
arXiv:2609.21437v1 Announce Type: cross Abstract: We propose LoG-VGGT, a memory-efficient framework for long-sequence 3D reconstruction that balances local temporal modeling with global camera consistency. Instead of rel…
- arXiv cs.AIresearchInterference-Driven Clustered Optimisation for FM Spectrum Coordination
arXiv:2609.21441v1 Announce Type: cross Abstract: Cross-border FM spectrum coordination involves protecting foreign broadcasting services while preserving domestic coverage, amid increasingly large radio-planning dataset…
- arXiv cs.AIresearchAtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining
arXiv:2609.21461v1 Announce Type: cross Abstract: Embodied foundation models are constrained by the limited scale and diversity of robot demonstrations, motivating the use of large-scale egocentric human interaction data…
- arXiv cs.AIresearchOmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
arXiv:2609.21465v2 Announce Type: replace-cross Abstract: We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simulta…
- arXiv cs.AIresearchHE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
arXiv:2609.21484v1 Announce Type: cross Abstract: Homomorphic encryption (HE) has emerged as a promising approach to privacy-preserving machine learning (PPML), enabling computation directly over encrypted data. In HE-ba…
- arXiv cs.AIresearch2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation
arXiv:2609.21511v1 Announce Type: cross Abstract: This report describes our 2nd place solution to the HANDS 2026 workshop challenge (Dexterous Grasp Motion track) in conjunction with ECCV 2026. In this challenge, we addr…
- arXiv cs.AIresearchVidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration
arXiv:2609.21521v2 Announce Type: replace-cross Abstract: While Video Large Language Models (Video-LLMs) have recently demonstrated strong performance, reliably evaluating their fine-grained video understanding remains c…
- arXiv cs.AIresearchOneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios
arXiv:2609.21550v1 Announce Type: cross Abstract: Auto-bidding is central to computational advertising, where strategies must maximize advertisers' conversion value under economic constraints. It has evolved from rule-ba…
- arXiv cs.AIresearchOn Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
arXiv:2609.21561v1 Announce Type: cross Abstract: On-policy self-distillation provides dense, token-level supervision by conditioning a model on privileged information and distilling the resulting teacher distribution ba…
- arXiv cs.AIagentsGameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions
arXiv:2609.21562v2 Announce Type: replace-cross Abstract: Coding agents can modify and test code across large software projects. Game development is a domain where agents must implement gameplay rules. A game can end in…
- arXiv cs.AIresearchCityLearn v3: A Configurable Simulation and Evaluation Framework for Realistic Control Studies of Renewable Energy Communities
arXiv:2609.21570v1 Announce Type: cross Abstract: Renewable energy communities (RECs) coordinate buildings, photovoltaic generation, batteries, electric vehicles and flexible loads. Controller studies often simplify chan…
- arXiv cs.AIresearchMicro-Collaborative Poisoning: A Distributed Attack on RAG Systems
arXiv:2609.21573v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves large language models by grounding outputs in external knowledge sources, but this dependency also creates a surface for poi…
- arXiv cs.AIresearchPotential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation
arXiv:2609.21609v1 Announce Type: cross Abstract: Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the policy to learn both…
- arXiv cs.AIresearchSteering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30
arXiv:2609.21636v1 Announce Type: cross Abstract: Recent work applies human psychometric questionnaires to large language models to elicit moral and value profiles, but it is not clear whether these instruments measure a…
- arXiv cs.AIresearchChinese Competitive Debating Dataset and Benchmark
arXiv:2609.21637v2 Announce Type: replace-cross Abstract: Debate adjudication requires tracking how arguments develop through interaction, yet existing datasets rarely combine fine-grained debate transcripts with profess…
- arXiv cs.AIresearchSynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations
arXiv:2609.21650v1 Announce Type: cross Abstract: Fine-tuning Vision-Language-Action (VLA) models commonly relies on human teleoperation demonstrations, while reinforcement learning (RL) with sparse binary rewards faces…
- arXiv cs.AIresearchOutcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies
arXiv:2609.21659v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) policies solve the same manipulation task through different action interfaces, but task success alone does not establish whether thei…
- arXiv cs.AIresearchWhen Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap
arXiv:2609.21662v1 Announce Type: cross Abstract: Activation steering has become a widely used approach for controlling language models during explicit chain-of-thought (CoT) reasoning, motivating its extension to latent…
- arXiv cs.AIresearchSamsone: A Family of Open Small Audio Language Models for On-Device Inference
arXiv:2609.21666v1 Announce Type: cross Abstract: The success of Large Audio Language Models has driven the development of massive multimodal networks exceeding billions of parameters. However, the demand for privacy-pre…
- arXiv cs.AIresearchFrom Code Archival to Knowledge Graph: Bridging Software Heritage, COAR Notify and Wikidata
arXiv:2609.21667v2 Announce Type: replace-cross Abstract: Software is a first-class scientific object, yet validated links between source code and the scholarly record remain largely absent from the Linked Open Data (LOD…
- arXiv cs.AIagentsCIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
arXiv:2609.21686v1 Announce Type: cross Abstract: Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval, or tool-use pipelines, which makes it difficult to distinguish…
- arXiv cs.AIresearchTERMon: Detecting Persistent Behavioral Threats in Edge AI via Hardware-Native Ternary Runtime Monitor
arXiv:2609.21713v1 Announce Type: cross Abstract: Edge AI accelerators are increasingly deployed in safety-critical environments, where model outputs may control physical actuators, make access-control decisions, or trig…
- arXiv cs.AIresearchCIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords
arXiv:2609.21722v1 Announce Type: cross Abstract: Chinese social media has generated a vast and continually evolving lexicon of internet buzzwords whose meanings are often non-literal and deeply rooted in local cultural…
- arXiv cs.AIresearchBalanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentation
arXiv:2609.21743v1 Announce Type: cross Abstract: Entropy minimization is a standard objective for test-time adaptation (TTA), but it can fail in imbalanced binary segmentation. Unlike image classification, dense segment…
- arXiv cs.AIresearchForceTwin: Physics-informed Digital Twins for Robotic Manipulation from Instrumented Human Interaction
arXiv:2609.21751v1 Announce Type: cross Abstract: Manipulating objects requires understanding not only their motion, but also the physical properties that determine it. For articulated objects, these include inertia, fri…
- arXiv cs.AIagentsAn Agentic Just-in-Time Adaptive Intervention System for Personalized Sleep Support: Proof-of-Concept Study with N of 1 Data
arXiv:2609.21805v1 Announce Type: cross Abstract: Background: Just-in-time adaptive interventions (JITAIs) can use behavioral data to adapt support to changing contexts, but many rely on predefined rules and manual confi…
- arXiv cs.AIresearchMatrix AdaGrad: Row-wise and Column-wise Adaptive Subgradient Methods
arXiv:2609.21815v2 Announce Type: replace-cross Abstract: Adaptive optimization methods such as AdaGrad and Adam are widely used in modern deep neural network training, but their adaptive scaling is primarily designed fo…
- arXiv cs.AIagentsTouvigation: Embodied Adaptive Object Acquisition for Blind and Low-Vision Users in Unfamiliar Indoor Environments
arXiv:2609.21828v1 Announce Type: cross Abstract: Blind and low-vision users often face challenges when locating and physically acquiring objects in unfamiliar indoor environments. Existing vision-language-model-based as…