AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchLimits of Confidence in Diffusion
arXiv:2609.20581v2 Announce Type: replace Abstract: Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position d…
- arXiv cs.AIresearchPAA: The Probabilistic Allen Algebra: A Generative and Complete Probabilistic Extension of Allen's Interval Relations
arXiv:2609.20634v1 Announce Type: new Abstract: Allen's interval algebra is a qualitative calculus for temporal relations, but its thirteen base relations are crisp predicates over exact interval boundaries. This is inad…
- arXiv cs.AIresearchOwnership in AI-Assisted Everyday Tasks
arXiv:2609.20658v1 Announce Type: new Abstract: When does work done with AI still feel like ours? As AI becomes woven into everyday tasks, we must examine what happens to our sense of ownership and contribution when a ma…
- arXiv cs.AIagentsDeep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
arXiv:2609.20722v1 Announce Type: new Abstract: Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses L…
- arXiv cs.AIresearchQ&A on Any Spreadsheet Requires Interpreting Its Grid Structure
arXiv:2609.20732v1 Announce Type: new Abstract: Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improv…
- arXiv cs.AIagentsRAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
arXiv:2609.20754v1 Announce Type: new Abstract: Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing retrieval-augmented gen…
- arXiv cs.AIagentsAn Empirical Study of Harness Design for Coding Agents
arXiv:2609.20804v1 Announce Type: new Abstract: Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates h…
- arXiv cs.AIresearchOptimal Transport Metric Learning for Feature Alignment in Partially Supervised Segmentation
arXiv:2609.19176v1 Announce Type: cross Abstract: Multi-organ segmentation is often challenged by partially annotated datasets and domain shifts across different imaging sources. To address these limitations, we propose…
- arXiv cs.AIresearchCode-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code
arXiv:2609.19199v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in legal logic and evidenc…
- arXiv cs.AIresearchREACT: A Fully Spiking State-Space Model for Real-Time Event-Driven Temporal Perception
arXiv:2609.19204v1 Announce Type: cross Abstract: Robotic systems operating in dynamic environments require visual perception that evolves continuously with the incoming sensory stream. Event cameras provide microsecond…
- arXiv cs.AIresearchMeshKV: A Network-on-Chip KV Cache Fabric for Scalable Transformer Decoding Accelerators
arXiv:2609.19207v1 Announce Type: cross Abstract: Autoregressive transformer decoding is constrained by irregular key-value (KV) cache movement on tiled accelerators. Prior compression and DRAM-placement systems still co…
- arXiv cs.AIresearchNot All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation
arXiv:2609.19210v1 Announce Type: cross Abstract: Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test splits. Reported accu…
- arXiv cs.AIresearchLayer-wise Curriculum Learning for Efficient LLM Compression
arXiv:2609.19213v1 Announce Type: cross Abstract: In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from the teacher model to…
- arXiv cs.AIresearchPerceptual Refinement of an End-to-End Video Streaming Pipeline via Generative AI Layers
arXiv:2609.19215v1 Announce Type: cross Abstract: Traditional codecs treat every region of a frame alike; a generative layer can instead degrade the regions a viewer attends to least and reconstruct them at the client. W…
- arXiv cs.AIagentsPAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows
arXiv:2609.19226v1 Announce Type: cross Abstract: AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a final answer appears: a…
- arXiv cs.AIagentsThe AR Fairness Metamodel: A Structured Framework for Fairness Measures
arXiv:2609.19234v1 Announce Type: cross Abstract: This paper presents the AR fairness metamodel, a framework designed to represent, analyze, and compare different fairness scenarios. The metamodel considers key elements,…
- arXiv cs.AIresearchYNU-HPCC at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Using Multiple Prediction Headers
arXiv:2609.19238v1 Announce Type: cross Abstract: This paper describes the participation of the YNU-HPCC team in subtask A of task 11, Bridging the Gap in Text-Based Emotion at SemEval-2025. Our best-performing system em…
- arXiv cs.AIresearchRobust Conformal Intrusion Detection via Traffic-Aware Calibration and Attack-Orbit Invariance
arXiv:2609.19241v1 Announce Type: cross Abstract: Large language models fine-tuned for network intrusion detection emit single-point predictions without statistical validity guarantees. Conformal prediction supplies a fi…
- arXiv cs.AIresearchRandomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices
arXiv:2609.19243v1 Announce Type: cross Abstract: Spectral co-clustering is a useful tool for discovering latent structure in word-document matrices, but its reliance on singular value decomposition (SVD) can make standa…
- arXiv cs.AIresearchPhysics-Informed Hemodynamic Modeling for Data-Free Prediction and Sparse-Data Assimilation
arXiv:2609.19290v1 Announce Type: cross Abstract: Clinical decision-making for coronary intervention relies mainly on angiography and fractional flow reserve (FFR). However, angiography is two-dimensional and lacks depth…
- arXiv cs.AIresearchWhy Pretraining Fails to Share Cross-Lingual Knowledge
arXiv:2609.19291v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made remarkable progress in the processing and modeling of many languages. Yet, unlike human multilinguals, they exhibit surprisingly li…
- arXiv cs.AIresearchGAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning
arXiv:2609.19315v1 Announce Type: cross Abstract: Large language models (LLMs) provide a flexible interface for long-horizon robot planning, but generated plans often fail to respect embodiment constraints, recover from…
- arXiv cs.AIresearchAUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
arXiv:2609.19325v1 Announce Type: cross Abstract: Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket refusal on benign requ…
- arXiv cs.AIagentsKinematics-Grounded Agentic AI for Robotic Additive Manufacturing Process Planning
arXiv:2609.19347v1 Announce Type: cross Abstract: Robotic additive manufacturing (AM) extends material-extrusion printing beyond gantry kinematics but makes process planning robot-dependent. A slicer-generated plan that…
- arXiv cs.AIresearchCan Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment
arXiv:2609.19354v1 Announce Type: cross Abstract: Automated action quality assessment (AQA) in Olympic sports remains a challenging task due to the complexity of human motion and the subjectivity inherent in expert judgi…
- arXiv cs.AIresearchHow to Guide Your Language Flow
arXiv:2609.19356v1 Announce Type: cross Abstract: We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing diffusion model to con…
- arXiv cs.AIresearchLinePilot Digitizer: Line-Plot Recovery with Manual and Automatic Calibration
arXiv:2609.19377v1 Announce Type: cross Abstract: Recovering numerical series from line plots requires accurate axis calibration and reliable curve extraction. We present LinePilot Digitizer (LinePilot), which combines c…
- arXiv cs.AIresearchRiemannian--Lorentz Fusion of Vision Transformers and State-Space Models
arXiv:2609.19384v1 Announce Type: cross Abstract: Scaling deep learning faces critical bottlenecks: data exhaustion, exponential training costs, and resource concentration. Model merging combines pre-trained checkpoints…
- arXiv cs.AIresearchEfficient Nash Equilibrium Computation for Cybersecurity Games
arXiv:2609.19399v2 Announce Type: replace-cross Abstract: Game-theoretic analyses of cyber defence often compute equilibria of games whose payoffs exist only as the output of a simulator. Iterative equilibrium-finding me…
- arXiv cs.AIagentsFrom Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation
arXiv:2609.19413v1 Announce Type: cross Abstract: Robot manipulation policies are improving quickly, and real-robot evaluation remains the standard evidence for that progress. It still relies on a human to reset the scen…
- arXiv cs.AIresearchPredict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models
arXiv:2609.19441v1 Announce Type: cross Abstract: World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization reduces memory and can…
- arXiv cs.AIresearchFrom Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning
arXiv:2609.19445v1 Announce Type: cross Abstract: The rapid expansion of multimodal models has surfaced formidable bottlenecks in computation, memory, and deployment, catalyzing the rise of Efficient Multimodal Learning…
- arXiv cs.AIagentsEfficiently Linking Unstructured Data for Multi-step Reasoning
arXiv:2609.19491v1 Announce Type: cross Abstract: Modern LLMs and AI agents increasingly support data engineering workflows that integrate evidence from unstructured sources. Such pipelines typically do data retrieval, i…
- arXiv cs.AIagentsFor Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances
arXiv:2609.19504v1 Announce Type: cross Abstract: As model-generated content is increasingly consumed by other model instances in automated workflows, a practically important question arises: can a model embed a signal i…
- arXiv cs.AIresearchCoreSense: Traceable Failure Recall and Conflict-Aware Belief Gating for Auditable Robot Decisions
arXiv:2609.19512v1 Announce Type: cross Abstract: Robots can recall prior failures without knowing whether recalled evidence remains valid, conflicts with current observations, or is sufficient to guide a decision. We pr…
- arXiv cs.AIagentsAURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation
arXiv:2609.19527v1 Announce Type: cross Abstract: Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More importantly, a…
- arXiv cs.AIresearchDetecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication
arXiv:2609.19531v1 Announce Type: cross Abstract: We propose PaRID (PaRallel Instruction Duplication), a software-directed soft error detection framework that requires only compile-time effort for multithreading parallel…
- arXiv cs.AIresearchCompressed Active Subspaces for Scalable Bayesian Inference
arXiv:2609.19539v1 Announce Type: cross Abstract: Active subspace methods provide a framework for quantifying predictive uncertainty in high-dimensional models by identifying and performing inference along parameter dire…
- arXiv cs.AIresearchA Multi-Modal Generative Model for Tomato Disease Leaves Understanding
arXiv:2609.19555v1 Announce Type: cross Abstract: Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting visual and textual in…
- arXiv cs.AIagentsLarge Language Model Agents for Evidence Based Genetic Disease Severity Classification
arXiv:2609.19569v2 Announce Type: replace-cross Abstract: Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial panels vary…
- arXiv cs.AIresearchCliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives
arXiv:2609.19585v1 Announce Type: cross Abstract: In mental health care, reasoning over patient journeys is a key task for clinicians. Yet these journeys, encompassing a longitudinal progression of biological, psychologi…
- arXiv cs.AIagentsRed-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents
arXiv:2609.19587v2 Announce Type: replace-cross Abstract: To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs (Auto…
- arXiv cs.AIresearchForm Over Content In Gradient-Based Data Attribution Methods
arXiv:2609.19589v1 Announce Type: cross Abstract: Data attribution methods using gradient similarity are widely used to analyze and select training data for large language models, but what gradient similarity actually me…
- arXiv cs.AIagentsDeltaSelect: Affordable A/B Testing for Coding Agents
arXiv:2609.19607v1 Announce Type: cross Abstract: Coding-agent benchmarks are built for broad and comprehensive comparisons, not frequent development decisions. Individual runs vary, full suites are expensive, and the be…
- arXiv cs.AIresearchTacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation
arXiv:2609.19613v2 Announce Type: replace-cross Abstract: Dexterous food manipulation requires control under deformation, occlusion, and uncertain contact. We present TacSushi, a tactile-grounded, Cosmos3-based world-act…
- arXiv cs.AIresearchSemantic Layer Induction from Raw Telemetry via Hierarchical LLM and RAG Abstraction
arXiv:2609.19615v1 Announce Type: cross Abstract: Modern applications generate massive volumes of raw telemetry data, but translating those noisy, heterogeneous event streams into actionable business insights remains a f…
- arXiv cs.AIagentsDataCanvas-EDU: An Agentic Framework for Instructor-Guided Synthetic Data Generation in Business Analytics Education
arXiv:2609.19617v2 Announce Type: replace-cross Abstract: Business analytics education requires diverse datasets to support different learning objectives, student backgrounds, and analytical tasks. Real-world data can be…
- arXiv cs.AIagentsSelf-Evolving Search Index
arXiv:2609.19656v1 Announce Type: cross Abstract: Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represen…
- arXiv cs.AIagentsTrading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes
arXiv:2609.19705v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents already trade real capital, and builders copy a few published designs that share models and news feeds, so one shock reaches man…
- arXiv cs.AIresearchLearn Your Own Thoughts: Abstract Token Curriculum
arXiv:2609.19717v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved remarkable reasoning capabilities by utilizing chain-of-thought (CoT) as a scratchpad for intermediate stages of thinki…