AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsReinforcing Agentic Creativity in Scientific Ideation with Night Science
arXiv:2609.35706v1 Announce Type: new Abstract: Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous and predictable outputs, limiting their utility for o…
- arXiv cs.AIagentsFailure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models
arXiv:2609.35732v1 Announce Type: new Abstract: Tool-using agents can fail twice: a required tool can fail, and the agent can then report success without the evidence needed to justify it. Existing benchmarks often entan…
- arXiv cs.AIagentsShockingly Simple Self-retrospection Improves Agentic Models Without RL
arXiv:2609.35741v1 Announce Type: new Abstract: People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a…
- arXiv cs.AIagentsFinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents
arXiv:2609.35744v2 Announce Type: replace Abstract: Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchm…
- arXiv cs.AIresearch$l_{1-2}$ GLasso: $L_{1-2}$ Regularized Multi-task Graphical Lasso for Joint Estimation of eQTL Mapping and Gene Network
arXiv:2301.02225v1 Announce Type: cross Abstract: A critical problem in genetics is to discover how gene expression is regulated within cells. Two major tasks of regulatory association learning are : (i) identifying SNP-…
- arXiv cs.AIresearchSciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing
arXiv:2602.09809v3 Announce Type: cross Abstract: Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing…
- arXiv cs.AIresearchChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports
arXiv:2609.31629v1 Announce Type: cross Abstract: Structured phenotype extraction from radiology reports supports cohort construction, quality auditing, and clinical analytics, but practical deployment requires local inf…
- arXiv cs.AIresearchWhat Next-Event Accuracy Cannot See: Closed-Loop Evaluation of Emergency Department Trajectory Simulators
arXiv:2609.31635v1 Announce Type: cross Abstract: Clinical trajectory models are usually evaluated by next-event accuracy on observed histories. Simulation is different: models must condition on their own generated event…
- arXiv cs.AIresearchEnergy-aware frugal Bayesian optimization
arXiv:2609.31638v1 Announce Type: cross Abstract: Modern design optimization frameworks aim first and foremost for models with the most accurate predictions without balancing computational overhead. It remains a reason w…
- arXiv cs.AIresearchWhen Does Domain Adaptation Help on Physical Vibration Sensors? A Held-Out-Bearing Study of Neural-Operator and Convolutional Models
arXiv:2609.31639v1 Announce Type: cross Abstract: Diagnosing rolling-element bearing faults from vibration is a canonical physical-sensing task and a widely used benchmark for domain adaptation under operating-condition…
- arXiv cs.AIresearchMeasure Learning at Steady State: A BIRD-SQL Formula 1 Case Study
arXiv:2609.31640v1 Announce Type: cross Abstract: Continual Learning Bench scores learning as short-horizon gain versus a reset baseline and finds naive full-context ICL strongest among the memories it tested. We treat I…
- arXiv cs.AIresearchInformation Design Against Gaming and Learning Adversaries
arXiv:2609.31643v1 Announce Type: cross Abstract: A principal who deploys a binary classifier with an abstention option must decide which queries the mechanism abstains on. The right choice depends on the adversary. A ga…
- arXiv cs.AIresearchMaD-RL: Matching Distributions for Calibrating LLMs with Reinforcement Learning
arXiv:2609.31644v1 Announce Type: cross Abstract: Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from binary verifiers…
- arXiv cs.AIresearchSTAR: Adaptive Spatial-Temporal Normalization for Unified Microservice Incident Management
arXiv:2609.31645v2 Announce Type: replace-cross Abstract: Automated incident management in large-scale microservice systems relies on learning robust representations from multimodal observability data, including metrics,…
- arXiv cs.AIresearchMeasurement-Error-Aware Causal Distributed-Lag Quantile Modeling of Indoor Air Pollution and Short-Term Lung-Function Deterioration
arXiv:2609.31646v1 Announce Type: cross Abstract: Low-cost indoor air-quality sensors could support personalized asthma prevention, but their nonlinear measurement error, delayed exposure effects, time-varying confoundin…
- arXiv cs.AIagentsTyped Temporal Interaction Features for Simulation-Backed Forecasting of Open-Source Game Release Incidents
arXiv:2609.31647v1 Announce Type: cross Abstract: Open-source video-game quality depends on inter-actions among code, assets, configuration, tests, contributors, and issue workflows, yet conventional defect predictors us…
- arXiv cs.AIresearchEnergy Vision--Language--Action: A Controlled Multimodal Benchmark for Intent-Conditioned Residential Energy Management
arXiv:2609.31648v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are studied mainly in robotics, where visual observations and language instructions are mapped to physical actions. This paper introdu…
- arXiv cs.AIresearchFrom Hand-Crafted to LLM-Based Variation Operators in Metaheuristics: A Tutorial
arXiv:2609.31649v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being employed as variation operators in metaheuristics, generating or modifying candidate solutions, heuristics, or program…
- arXiv cs.AIresearchPalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions
arXiv:2609.31651v1 Announce Type: cross Abstract: Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) handle culturally dive…
- arXiv cs.AIresearchOpen-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Rendering
arXiv:2609.31652v1 Announce Type: cross Abstract: We present Open-Qwen-Music, an open reconstruction of Qwen-Music and a fully specified research system for text-to-music generation that couples LLM-based semantic compos…
- arXiv cs.AIresearchTemporal-Attention Head Specialization During Video Diffusion Training
arXiv:2609.31654v2 Announce Type: replace-cross Abstract: Video diffusion transformers depend on temporal attention to coordinate information across frames, yet nearly everything known about this mechanism comes from ana…
- arXiv cs.AIresearchFrom Phase Transition to Systemic Failure: A Decoupled Analytics Framework for GNN Robustness
arXiv:2609.31656v1 Announce Type: cross Abstract: Data quality is a major bottleneck for the reliable deployment of graph neural networks (GNNs) in real-world graph mining tasks. Among various sources of degradation, lab…
- arXiv cs.AIresearchEnhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling
arXiv:2609.31657v1 Announce Type: cross Abstract: Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not well characterized.…
- arXiv cs.AIresearchCross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification
arXiv:2609.31658v1 Announce Type: cross Abstract: Ship classification from Synthetic Aperture Radar (SAR) imagery is a critical computer vision task, yet the robustness of models under deployment shifts remains unclear.…
- arXiv cs.AIresearchParser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents
arXiv:2609.31660v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) pipelines are typically assembled from independently-chosen components -- a document parser, a chunking strategy, and an embedding mo…
- arXiv cs.AIresearchWhat Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy Banks
arXiv:2609.31664v1 Announce Type: cross Abstract: Recent work suggests that obscure language registers can weaken large language model refusal behavior, especially when paired with black-box prompt optimization. It remai…
- arXiv cs.AIresearchAge-Adaptive Handwriting Reconstruction from an IMU-Based Digital Pen through Shared Representations and Domain-Specific Heads
arXiv:2609.31666v1 Announce Type: cross Abstract: Digital pens are widely used to capture handwriting on digital devices, enabling precise trace recording and enhancing human-computer interaction. However, most are bundl…
- arXiv cs.AIresearchQuery-aligned video frame selection for long video understanding
arXiv:2609.31668v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) process multimodal inputs by converting text, images, and videos into token sequences that are subsequently processed by a backbo…
- arXiv cs.AIresearchUnsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data
arXiv:2609.31671v1 Announce Type: cross Abstract: Event cameras are well suited to pedestrian crossing detection, and spiking neural networks (SNNs) can process their output natively, but current SNN detectors are traine…
- arXiv cs.AIagentsActive Causal Discovery Benchmark: Evaluating LLM Agents Under Budgeted Interventions
arXiv:2609.31675v1 Announce Type: cross Abstract: We introduce the Active Causal Discovery Benchmark (ACDB), an SCM-grounded environment for evaluating whether LLM agents recover causal graph structure from observations…
- arXiv cs.AIagentsA Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset
arXiv:2609.31677v1 Announce Type: cross Abstract: Face recognition is widely deployed in surveillance, access control, and forensic workflows, yet accuracy degrades sharply once the face is occluded by accessories, foreg…
- arXiv cs.AIresearchToward AI-Assisted Poultry Coccidiosis Diagnosis: Evaluating Gemini and BiomedParse on Eimeria Microscopy Images
arXiv:2609.31679v1 Announce Type: cross Abstract: Coccidiosis caused by Eimeria parasites is a major economic burden in poultry production, and effective control depends on accurate species-level diagnosis. This study ev…
- arXiv cs.AIresearchDoes Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?
arXiv:2609.31680v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representations by predicting t…
- arXiv cs.AIagentsAutonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression
arXiv:2609.31683v1 Announce Type: cross Abstract: This work presents an end-to-end demonstration of autonomous machine learning research conducted by an agent skill on consumer hardware. The demonstration evaluates an FF…
- arXiv cs.AIresearchWhat does FFN compression change downstream? Same-state causal restoration in diffusion language models
arXiv:2609.31685v1 Announce Type: cross Abstract: Diffusion language models (DLMs) enable flexible, parallel generation, but their iterative denoising remains computationally expensive, motivating increasingly aggressive…
- arXiv cs.AIresearchAdapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection
arXiv:2609.31690v1 Announce Type: cross Abstract: Explainable Artificial Intelligence (XAI) solutions are essential for building trust in AI technologies and their integration in real manufacturing lines. However, most e…
- arXiv cs.AIresearchIntegrated Deep Learning Framework Designed on Hybrid Optimization Strategies for Automated Health Detection and Analysis in Silkworms
arXiv:2609.31701v1 Announce Type: cross Abstract: A Hybrid Residual Attention Network is proposed for accurately classifying silkworm images into six different classes, including healthy and diseased states. It uses resi…
- arXiv cs.AIresearchCan't Find Waldo: Evaluating VLMs' Sensitivity to Image Resolution and Detail Level
arXiv:2609.31706v1 Announce Type: cross Abstract: Visual Language Models (VLMs) have achieved remarkable success across diverse tasks, yet they struggle with high-resolution inputs where critical information resides in s…
- arXiv cs.AIagentsAgentic Video Understanding: A Survey
arXiv:2609.31713v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyo…
- arXiv cs.AIagentsMM-VeriRec: Failure-Guided Fusion for Verifiable Agentic Multimodal Recommendation
arXiv:2609.31718v1 Announce Type: cross Abstract: Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and a visually impossib…
- arXiv cs.AIresearchFrequency-Domain AI-Generated Image Detection: Exploring Decoder and Channel Attention for Feature Refinement
arXiv:2609.31723v1 Announce Type: cross Abstract: With the rapid progress of AI, the number of AI-generated images has increased significantly in recent years. However, the increasing variety of image generation models m…
- arXiv cs.AIresearchSWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation
arXiv:2609.31725v1 Announce Type: cross Abstract: Video Object Segmentation (VOS) aims to accurately segment target objects from consecutive video frames and track the changes of the objects in each frame of the video. C…
- arXiv cs.AIresearchHigh-Capacity Robust Medical Image Exfiltration via Neural Network Weight Replacement
arXiv:2609.31726v1 Announce Type: cross Abstract: Collaborative medical AI platforms allow researchers to train models on sensitive imaging data while restricting data export. However, trained models can serve as covert…
- arXiv cs.AIresearchGERIS: A Game-Theoretic Framework for Filtering Instance-Dependent Label Noise in License Plate Data Augmentation
arXiv:2609.31731v1 Announce Type: cross Abstract: In this paper, we propose GERIS, a game-theoretic framework for instance selection in the data augmentation phase of license plate recognition systems. During augmentatio…
- arXiv cs.AIresearchLukeNet: A lightweight CNN integrated with an XAI model for Smart acute lymphoblastic leukemia detection and management
arXiv:2609.31736v1 Announce Type: cross Abstract: Acute Lymphoblastic Leukemia (ALL) patients require early, accurate detection to enable timely treatment and effective patient management. A Convolutional Neural Network…
- arXiv cs.AIagentsWhat Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery
arXiv:2609.31760v1 Announce Type: cross Abstract: Can a robot improve itself the way coding agents now improve software? We built an agentic system to find out. It watches a robot fail, works out which capability is miss…
- arXiv cs.AIagentsRobot Manipulation with GPT-6-Astra: Body Knowledge, Experience Reuse, Emergent Skills, and Sim2Real Transfer
arXiv:2609.31770v1 Announce Type: cross Abstract: General-purpose multimodal agents can write robot-control programs, but repeated exploration and model-mediated action selection can make execution slow. We study how ext…
- arXiv cs.AIresearchPRIME-ANC: Path-Ratio-Informed Modeling for Efficient Neural Filter Synthesis in Active Noise Control
arXiv:2609.31772v1 Announce Type: cross Abstract: Changes in listener acoustics require active noise control (ANC) filters to be redesigned for new acoustic paths. We introduce PRIME-ANC, a shared neural synthesizer that…
- arXiv cs.AIagentsTimed Rule-Based Supervision of an End-to-End Autonomous Parking Policy
arXiv:2609.31773v1 Announce Type: cross Abstract: We study whether a manually specified runtime supervisor can correct recurring failures of an existing end-to-end parking policy in a fixed CARLA parking lot. The vision-…
- arXiv cs.AIresearchOptimal transport meets speech: a tutorial review
arXiv:2609.31787v1 Announce Type: cross Abstract: Optimal Transport (OT) provides a principled framework for comparing and transforming probability distributions while preserving geometric structure. Recently, OT has gai…