AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMARS: Malware Analysis with Rule-Based Scoring of LLM Claims
arXiv:2610.09553v1 Announce Type: cross Abstract: Large language models can triage malware through direct verdicts or behavioral claims scored by an external policy. We present MARS, a malware triage framework, and compa…
- arXiv cs.AIresearchHow Do LLMs Change Predictions Under Negation?
arXiv:2610.09571v2 Announce Type: replace-cross Abstract: Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source and closed…
- arXiv cs.AIagentsCorrect Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs
arXiv:2610.09581v1 Announce Type: cross Abstract: Forensic reconstruction of LLM-agent actions requires not only recovering the correct value, but establishing which preserved record supports that finding. Tool logs, gen…
- arXiv cs.AIresearchCollaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
arXiv:2610.09587v1 Announce Type: cross Abstract: Reasoning capabilities are critical for advancing Large Language Models, yet current approaches either require massive computational budgets or struggle to effectively di…
- arXiv cs.AIresearchAdaptive Code Generation for Controlling Robots
arXiv:2610.09588v1 Announce Type: cross Abstract: Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based auton…
- arXiv cs.AIresearchStructured pre-generation elicitation versus single-shot prompting in AI-assisted enterprise decision-making: a randomised online experiment
arXiv:2610.09593v1 Announce Type: cross Abstract: Generative AI speeds, and mostly improves, professional work, but there is concern that users who delegate both the production and the evaluation of an answer may accept…
- arXiv cs.AIresearchWhich Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
arXiv:2610.09607v1 Announce Type: cross Abstract: Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We prop…
- arXiv cs.AIagentsCoding-Agent Benchmarks Should Match Their Users' Task Flows
arXiv:2610.09633v2 Announce Type: replace-cross Abstract: The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetB…
- arXiv cs.AIagentsCircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies
arXiv:2610.09643v1 Announce Type: cross Abstract: Drug discovery for neurological disease has traditionally centered on the molecules altered by disease. But the molecules that cause pathology are not necessarily the bes…
- arXiv cs.AIresearchReal-world application of deep learning in large-scale seismic interference attenuation: A case study in the Camie field of Angola
arXiv:2610.09663v1 Announce Type: cross Abstract: In marine seismic acquisition, seismic interference (SI) occurs when energy from nearby external seismic source(s) is captured. It typically appears as coherent noise wit…
- arXiv cs.AIresearchCERO: Where and When to Allocate Rollouts for RL Post-Training
arXiv:2610.09679v1 Announce Type: cross Abstract: Adaptive rollout methods for group-relative reinforcement learning typically allocate a fixed per-update budget across prompts. We instead study how to coordinate a finit…
- arXiv cs.AIagentsFrom Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
arXiv:2610.09684v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS…
- arXiv cs.AIresearchFew-Shot Learning for Personalised Automated Pain Assessment
arXiv:2610.09692v1 Announce Type: cross Abstract: Pain perception varies substantially across individuals, making it difficult for population-based classifiers to generalise across all subjects in a dataset. One way to a…
- arXiv cs.AIresearchWhat Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?
arXiv:2610.09700v2 Announce Type: replace-cross Abstract: Synthetic hard negatives generated in the representation space have proven effective for unimodal self-supervised learning, but transferring this idea to vision-l…
- arXiv cs.AIresearchHealthy skepticism in AI: a data visualization research agenda
arXiv:2610.09740v1 Announce Type: cross Abstract: Research in data visualization of artificial intelligence (AI) models has historically focused on enhancing trust through visual explanations of AI. The trustworthiness l…
- arXiv cs.AIresearchUnrolled Flow Models for Reasoning
arXiv:2610.09759v1 Announce Type: cross Abstract: Flow matching enables language generation in few steps, but whether additional integration steps improve reasoning remains unclear. We prove that a flow parameterized by…
- arXiv cs.AIresearchPARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency
arXiv:2610.09761v1 Announce Type: cross Abstract: Text-to-point-cloud localization estimates a position in a city-scale 3D map from descriptions of surrounding objects. Existing coarse-to-fine methods retrieve submaps us…
- arXiv cs.AIagentsBeyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving
arXiv:2610.09763v2 Announce Type: replace-cross Abstract: Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly attractiv…
- arXiv cs.AIresearchArtificial intelligence pathways from weather to climate
arXiv:2610.09770v1 Announce Type: cross Abstract: Deep learning has made rapid advances in weather forecasting: autoregressive models trained on atmospheric reanalyses now rival dynamical models across nowcasting, medium…
- arXiv cs.AIagentsDecoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
arXiv:2610.09772v2 Announce Type: replace-cross Abstract: Edge language-model agents must hold a persona and reason correctly at once, in one context window that fills with history and persona instructions. We study what…
- arXiv cs.AIresearchMIRROR: From Imitation to Internalization in LLM Personalization
arXiv:2610.09795v1 Announce Type: cross Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap in existing fine-tu…
- arXiv cs.AIresearchDisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
arXiv:2610.09802v1 Announce Type: cross Abstract: Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. Howev…
- arXiv cs.AIresearchUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
arXiv:2610.09823v1 Announce Type: cross Abstract: Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, e…
- arXiv cs.AIresearchA Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks
arXiv:2610.09835v1 Announce Type: cross Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using often-inaccessible o…
- arXiv cs.AIresearchFully Interpretable Minimal Transformers: From Geometry to Algorithm
arXiv:2610.09838v1 Announce Type: cross Abstract: We present a framework for building and interpreting minimal transformer models. By constraining a transformer's embedding dimension and head size to 2, we enable full tw…
- arXiv cs.AIresearchStream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case Study
arXiv:2610.09848v1 Announce Type: cross Abstract: Inverse design in engineering often runs into a simple problem. Each labeled training sample must be produced through expensive simulation, so building a large dataset is…
- arXiv cs.AIagentsTraining Advisors for LLM Agents from Task Outcomes
arXiv:2610.09858v1 Announce Type: cross Abstract: Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has shown that natural-lan…
- arXiv cs.AIagentsDeadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks
arXiv:2610.09870v1 Announce Type: cross Abstract: Vehicular edge computing (VEC) enables latency-sensitive applications by bringing computing and networking resources closer to vehicles. However, existing approaches ofte…
- arXiv cs.AIagentsAn AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modeling
arXiv:2610.09871v1 Announce Type: cross Abstract: Implicit modeling and Relative Geologic Time are geological modeling techniques that enable more efficient, faster, less biased and more reproducible modeling results. Fo…
- arXiv cs.AIresearchA Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
arXiv:2610.09891v1 Announce Type: cross Abstract: Human-Robot Collaboration (HRC) can facilitate mass customisation in Industry 4.0, with Reinforcement Learning from Human Feedback (RLHF) representing a promising approac…
- arXiv cs.AIresearchDefensive Sufficiency in a Stackelberg Model of AI Security
arXiv:2610.09892v2 Announce Type: replace-cross Abstract: Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead to effective repair…
- arXiv cs.AIresearchQCATS: Query Context-Aware Transformer Slicing for Efficient Predictive Query Processing
arXiv:2610.09894v1 Announce Type: cross Abstract: In-database predictive query processing increasingly applies Transformer-based models within relational pipelines. However, existing in-database inference typically expos…
- arXiv cs.AIresearchConstrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
arXiv:2610.09906v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated alerts and too few ana…
- arXiv cs.AIresearchRollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning
arXiv:2610.09914v1 Announce Type: cross Abstract: Reinforcement learning is crucial for improving large language models' reasoning and generalization. It relies on massive rollouts whose lengths become increasingly long-…
- arXiv cs.AIresearchKGATE : a Knowledge Graph Embedding Training Environment
arXiv:2610.09927v1 Announce Type: cross Abstract: Knowledge graph embedding (KGE) models encode the entities and relations of a knowledge graph into a low-dimensional latent space, enabling tasks such as classification o…
- arXiv cs.AIresearchItgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR
arXiv:2610.09934v1 Announce Type: cross Abstract: We describe the Itgan systems for the three ASR subtasks of NADI 2026, namely robust country-level ASR (1.1), mixed-dialect ASR (1.2), and Tunisian code-switched ASR (1.3…
- arXiv cs.AIresearchFast holographic inversion of superconducting domes
arXiv:2610.09938v1 Announce Type: cross Abstract: A holographic superconductor whose scalar mass depends on the gauge field strength, $M(\Fsq)$, reproduces a superconducting dome for a suitable $M$, and recovering that $…
- arXiv cs.AIresearchEfficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection
arXiv:2610.09993v1 Announce Type: cross Abstract: Spatial defect signatures on wafer bin maps (WBMs) trace yield loss to specific process faults, yet supervised classifiers recognize only the defect types seen during tra…
- arXiv cs.AIresearchTemporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories
arXiv:2610.09994v1 Announce Type: cross Abstract: Models with near-identical predictive performance can yield substantially different predictions, a phenomenon known as predictive multiplicity. Prior work has mostly stud…
- arXiv cs.AIresearchBeyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards
arXiv:2610.10000v1 Announce Type: cross Abstract: Adversarial attacks on bandits aim to mislead a learner toward a target arm while keeping the attack cost small. Existing attacks typically achieve this by suppressing no…
- arXiv cs.AIresearchTRACK: Telemetry-Based Racing Analysis and Coaching Kit in Sim Racing Games
arXiv:2610.10061v1 Announce Type: cross Abstract: This paper presents TRACK (Telemetry-Based Racing Analysis and Coaching Kit), which is a framework for analyzing driving performance in sim racing and profiling how indiv…
- arXiv cs.AIresearchComprehension Audits to Mitigate Risks from Automated AI Research
arXiv:2610.10064v1 Announce Type: cross Abstract: AI is already writing a majority of code for frontier AI labs. This creates a safety risk if there is insufficient human oversight. Existing work proposes minimum compreh…
- arXiv cs.AIresearchFrom Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs
arXiv:2610.10066v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in both visual understanding and code generation. However, existing benchmarks typicall…
- arXiv cs.AIresearchActivation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression
arXiv:2610.10085v1 Announce Type: cross Abstract: Post-training tensor-network compression replaces Transformer linear layers with Tensor Train (TT) or Tree Tensor Network (TTN) operators, but standard decompositions min…
- arXiv cs.AIresearchExperienceIndex: Artifact-Grounded Memory
arXiv:2610.10091v1 Announce Type: cross Abstract: Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans intera…
- arXiv cs.AIagentsKnow the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures
arXiv:2610.10126v1 Announce Type: cross Abstract: Multi-agent LLM systems coordinate task execution through exchanges of information among agents. When coordination breaks down, similar symptoms in execution traces can r…
- arXiv cs.AIagentsWhen Algorithmic Exploration Becomes Cheap: A Case Study of Agentic Research in EDA
arXiv:2610.10129v1 Announce Type: cross Abstract: As EDA researchers, we conducted eight deliberate trials of agentic algorithm exploration, selecting several topics outside our areas of depth. One faculty member and sev…
- arXiv cs.AIresearchDoes Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
arXiv:2610.10170v1 Announce Type: cross Abstract: Retrieval-augmented generation systems increasingly rely on document-structure treatments: structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata…
- arXiv cs.AIagentsBeyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents
arXiv:2610.10179v1 Announce Type: cross Abstract: Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning with Verifiable Rewa…
- arXiv cs.AIresearchEEG and Eye-Tracking Evidence That AI Disclosure Shapes Face Evaluation
arXiv:2610.10182v1 Announce Type: cross Abstract: AI-generated faces can be difficult to distinguish from real ones, leaving viewers to rely on source labels when judging an image. Yet prior work has made it difficult to…