AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchScaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
arXiv:2609.37842v1 Announce Type: cross Abstract: Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influence different behavio…
- arXiv cs.AIresearchIs manual software optimization a thing of the past?
arXiv:2609.37849v1 Announce Type: cross Abstract: Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditionally requires substan…
- arXiv cs.AIresearchHandAnthro: Automated Hand Anthropometry from a Single Image
arXiv:2609.37855v1 Announce Type: cross Abstract: Hand anthropometry supports protective-glove design, but existing measurement methods often require trained operators, specialized hardware, or manual landmarking. We pre…
- arXiv cs.AIresearchIt's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
arXiv:2609.37863v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model rather than incidental…
- arXiv cs.AIagentsAgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems
arXiv:2609.37864v1 Announce Type: cross Abstract: Agent harness bugs exhibit unique characteristics and remain challenging for state-of-the-art software agents to repair. Progress in this area is further hindered by exis…
- arXiv cs.AIresearchLearning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
arXiv:2609.37868v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail…
- arXiv cs.AIagentsExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving
arXiv:2609.37871v1 Announce Type: cross Abstract: Average performance on routine driving benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual…
- arXiv cs.AIresearchBoids of a Feather Flock Together - Evolving Prey Behaviours Under Different Predator Attack Strategies
arXiv:2609.37885v1 Announce Type: cross Abstract: Flocking and schooling are thought to have evolved partly as defences against predation, but how prey should balance social and escape tendencies may depend on the predat…
- arXiv cs.AIresearchBeyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR Prediction
arXiv:2609.37905v1 Announce Type: cross Abstract: Click-Through Rate prediction, a core task in recommendation and advertising systems, relies on modeling interactions among sparse categorical features. Explicit cross ne…
- arXiv cs.AIresearchGenerated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3
arXiv:2609.37911v1 Announce Type: cross Abstract: Scientific queries are often brief, while relevant papers use specialized vocabulary. Generated query expansion can bridge this mismatch, but earlier work suggests that i…
- arXiv cs.AIresearchThe Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
arXiv:2609.37914v1 Announce Type: cross Abstract: Fine-tuning large language models on narrow, misaligned tasks can undo their post-training alignment and induce novel misaligned behaviors -- a phenomenon known as \emph{…
- arXiv cs.AIresearchRLX: A Unified Multi-Backend Tensor Compiler and Distributed Runtime in Rust
arXiv:2609.37916v1 Announce Type: cross Abstract: Production machine learning (ML) stacks often split graph compilation and kernel execution across different layers and languages, making backend behavior, deployment guar…
- arXiv cs.AIresearchRollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation
arXiv:2609.37925v1 Announce Type: cross Abstract: Autoregressive (AR) video diffusion enables low-latency, streamable video generation, but prediction errors often accumulate over long rollouts. Training the generator on…
- arXiv cs.AIresearchDoes Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark
arXiv:2609.37938v1 Announce Type: cross Abstract: Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video acc…
- arXiv cs.AIresearchDagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
arXiv:2609.37972v1 Announce Type: cross Abstract: As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat. By q…
- arXiv cs.AIresearchOn Trajectory-Aware Training for Masked Diffusion Language Models
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The model is trained on ra…
- arXiv cs.AIresearch$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient
arXiv:2609.37976v2 Announce Type: replace-cross Abstract: LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capacity lies in th…
- arXiv cs.AIagentsBITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals
arXiv:2609.37993v2 Announce Type: replace-cross Abstract: The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence over a movie…
- arXiv cs.AIresearchNo Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection
arXiv:2609.38004v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies s…
- arXiv cs.AIresearchFrom Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection
arXiv:2609.38010v1 Announce Type: cross Abstract: Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety monitoring, data colle…
- arXiv cs.AIresearchAuditing Long-Term Memory Evaluation: Repeated Judging, Reader Variation, and Negative Controls
arXiv:2609.38021v2 Announce Type: replace-cross Abstract: This report audits evaluation of a long-term-memory retrieval chain on the 500 LongMemEval-S development questions. Its strongest historical reader lane scores 47…
- arXiv cs.AIresearchDr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models
arXiv:2609.38025v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD treats all teacher…
- arXiv cs.AIagentsdoPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving
arXiv:2609.38028v1 Announce Type: cross Abstract: Autonomous vehicles interacting with passengers through natural language must reason beyond immediate commands. Passenger intent may span multiple stages of behavior, dep…
- arXiv cs.AIresearchGender bias across LLMs is common and highly heterogeneous
arXiv:2609.38036v2 Announce Type: replace-cross Abstract: Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with real consequ…
- arXiv cs.AIagentsJaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL
arXiv:2609.38065v1 Announce Type: cross Abstract: Training agents to follow arbitrary instructions is an important goal of multi-task reinforcement learning (RL). Linear temporal logic (LTL) provides a precise and struct…
- arXiv cs.AIresearchNeural topology optimization of ship structures under propulsion machinery vibrations
arXiv:2609.38089v1 Announce Type: cross Abstract: Ship structural vibrations contribute to noise, fatigue, and equipment damage, while dynamic-compliance topology optimization can produce pathological designs near resona…
- arXiv cs.AIagentsCorrect Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interp…
- arXiv cs.AIresearchHow Local Mixing Encodes Relative Position in Global NoPE Attention
arXiv:2609.38109v1 Announce Type: cross Abstract: The attention operation is naively position invariant. However, positional information is fundamental to natural language, and therefore a variety of explicit position en…
- arXiv cs.AIresearchBreaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
arXiv:2609.38140v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes…
- arXiv cs.AIresearchBeyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
arXiv:2609.38155v1 Announce Type: cross Abstract: Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entiti…
- arXiv cs.AIresearchLeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
arXiv:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA). Although…
- arXiv cs.AIresearchSTEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
arXiv:2609.38169v1 Announce Type: cross Abstract: Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serv…
- arXiv cs.AIagentsSkill-Space Shooting for Autonomous Robot Policy Improvement
arXiv:2609.38178v1 Announce Type: cross Abstract: Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this improvement to scale a…
- arXiv cs.AIresearchImplementing Cumulative Functions with Generalized Cumulative Constraints
arXiv:2508.01751v3 Announce Type: replace Abstract: Modeling scheduling problems with conditional time intervals and cumulative functions has become a common approach when using modern commercial constraint programming s…
- arXiv cs.AIresearchSequence Variables: A Constraint Programming Computational Domain for Routing and Sequencing
arXiv:2510.09373v2 Announce Type: replace Abstract: Constraint Programming (CP) offers an intuitive, declarative framework for modeling Vehicle Routing Problems (VRP). While classical successor-based CP models can be ada…
- arXiv cs.AIagentsAgentic AI for Clustering and Relationship Discovery in Prediction Markets
arXiv:2512.02436v4 Announce Type: replace Abstract: Prediction market platforms list thousands of contracts whose logical and economic connections are implicit in their resolution rules. We introduce a hierarchical agent…
- arXiv cs.AIresearchNonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
arXiv:2602.05709v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) approximates the update of a pretrained weight matrix using the product of two low-rank matrices. However, standard LoRA follows an explicit-…
- arXiv cs.AIresearchBeyond Pixels: A Vector-to-Graph Framework for Reliable Schematic Auditing
arXiv:2602.11678v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even…
- arXiv cs.AIresearchFloCA: Towards Faithful and Logically Consistent Flowchart Reasoning
arXiv:2602.14035v2 Announce Type: replace Abstract: Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decision-making or operational procedures by following a domain-specific flowchart to ac…
- arXiv cs.AIagentsEvaluating Test-Time Scaling of General LLM Agents
arXiv:2602.18998v2 Announce Type: replace Abstract: LLM agents are increasingly expected to operate as general-purpose systems that resolve real-world user requests, yet their dynamic scaling behavior in realistic enviro…
- arXiv cs.AIresearchCIRCLE: A Framework for Evaluating AI from a Real-World Lens
arXiv:2602.24055v5 Announce Type: replace Abstract: This study proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI system outcomes in deploym…
- arXiv cs.AIresearchOntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation
arXiv:2604.05468v3 Announce Type: replace Abstract: Temporal knowledge graph (TKG) extrapolation is an important task that aims to predict future facts through historical interaction information within KG snapshots. A ke…
- arXiv cs.AIagentsRead the Paper, Write the Code: Agentic Reproduction of Social-Science Results
arXiv:2604.21965v2 Announce Type: replace Abstract: Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by asking: Can they reproduce…
- arXiv cs.AIresearchTimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization
arXiv:2605.01418v2 Announce Type: replace Abstract: Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing time-series generative…
- arXiv cs.AIagentsProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
arXiv:2605.06223v4 Announce Type: replace Abstract: Natural-language instance navigation becomes challenging when the initial user request does not uniquely specify the target instance. A practical agent should reduce th…
- arXiv cs.AIagentsProcess Matters more than Output for Distinguishing Humans from Machines
arXiv:2605.06524v3 Announce Type: replace Abstract: Reliable human-machine discrimination is becoming increasingly important as Large Language Models and autonomous agents are deployed in online settings. Existing approa…
- arXiv cs.AIagentsEquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
arXiv:2605.09278v2 Announce Type: replace Abstract: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerability: a single cor…
- arXiv cs.AIagentsAre Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows
arXiv:2605.14322v4 Announce Type: replace Abstract: Language agents are increasingly deployed in professional workflows, yet tutoring remains a high-stakes capability that existing evaluations only partially capture. Eff…
- arXiv cs.AIagentsCOLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning
arXiv:2605.14483v2 Announce Type: replace Abstract: Large language models (LLMs) provide a flexible foundation for multi-agent systems, but their effectiveness and computational cost depend critically on orchestration de…
- arXiv cs.AIagentsOttilie: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce
arXiv:2605.14542v2 Announce Type: replace Abstract: A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowledge, emotionall…