AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsUse and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents
arXiv:2610.12124v1 Announce Type: new Abstract: The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous exper…
- arXiv cs.AIresearchAn Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling
arXiv:2610.12129v1 Announce Type: new Abstract: A large body of research measures model coherence based on output variance without adequately considering competing causes. We identify two such causes, ambiguity and indif…
- arXiv cs.AIagentsOA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression
arXiv:2610.12134v1 Announce Type: new Abstract: Knee osteoarthritis (KOA) progression prediction can support patient monitoring, requiring the integration of multimodal data and multidomain expertise. Moreover, isolated…
- arXiv cs.AIagentsQ-Shaped Options for Hierarchical Reinforcement Learning
arXiv:2610.12135v1 Announce Type: new Abstract: Learning to tackle long-horizon, goal-conditioned tasks requires an agent to reason over extended timescales and act across a broad range of states. In principle, Hierarchi…
- arXiv cs.AIresearchInstruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization
arXiv:2610.12142v1 Announce Type: new Abstract: Electromagnetic spectrum monitoring increasingly requires flexible analysis beyond task-specific recognition and detection. Multimodal large language models offer a unified…
- arXiv cs.AIresearchLearning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models
arXiv:2610.12168v1 Announce Type: new Abstract: We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abil…
- arXiv cs.AIagentsRecursive Self-Improvement through Multi-Agent Self-Supervision
arXiv:2610.12176v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human exp…
- arXiv cs.AIresearchWhen Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees
arXiv:2610.12212v1 Announce Type: new Abstract: Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from…
- arXiv cs.AIagentsOne Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
arXiv:2610.12292v1 Announce Type: new Abstract: A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work pl…
- arXiv cs.AIresearchLearning Probabilistic Logic Programs with Functional Gradient Guided Language Models
arXiv:2610.12303v1 Announce Type: new Abstract: Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing dependencies as weigh…
- arXiv cs.AIresearchLooking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
arXiv:2610.12304v1 Announce Type: new Abstract: Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. In…
- arXiv cs.AIresearchA Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space
arXiv:2610.12306v1 Announce Type: new Abstract: Learning and problem solving depend critically on the structure of internal representations. While many modern data-driven artificial systems achieve strong predictive perf…
- arXiv cs.AIresearchVerdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems
arXiv:2610.12313v1 Announce Type: new Abstract: Large language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it is given. We test this directly across five models a…
- arXiv cs.AIagentsPrior or Feedback? What an LLM Uses When Adapting Neural Operators
arXiv:2610.12325v1 Announce Type: new Abstract: Do LLM scientific agents rely only on their initial task context, or do they adapt their decisions in response to experimental feedback? We study this question in neural op…
- arXiv cs.AIagentsCan AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
arXiv:2610.12341v1 Announce Type: new Abstract: Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain challenging. AI age…
- arXiv cs.AIresearchOvercoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
arXiv:2610.12345v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially different levels of pre…
- arXiv cs.AIagentsAccurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
arXiv:2610.12360v1 Announce Type: new Abstract: When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusion? Existing evaluati…
- arXiv cs.AIresearchCited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
arXiv:2610.12361v1 Announce Type: new Abstract: Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision follows from it. We te…
- arXiv cs.AIresearchHANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing
arXiv:2610.12363v1 Announce Type: new Abstract: Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education. However, existing document parsing and handwriting recognitio…
- arXiv cs.AIagentsOnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport
arXiv:2610.12375v1 Announce Type: new Abstract: Agents are deployed in applications from trip planners and stock trading to IT incident triage. In most cases, LLM agents work autonomously with minimal rule-based safeguar…
- arXiv cs.AIresearchGeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving
arXiv:2610.12391v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric e…
- arXiv cs.AIresearchHRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling
arXiv:2610.12393v2 Announce Type: replace Abstract: Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet capturing synergistic information remains challenging due…
- arXiv cs.AIresearchSearching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
arXiv:2610.12409v1 Announce Type: new Abstract: Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safety-related attributes, so models with similar overall…
- arXiv cs.AIagentsEcology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
arXiv:2610.12436v1 Announce Type: new Abstract: AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards. Together, th…
- arXiv cs.AIagentsBrickBench: Evaluating Agentic Brick Design
arXiv:2610.12452v1 Announce Type: new Abstract: We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies seman…
- arXiv cs.AIresearchOn the estimation and validity of AI time horizons---a statistical look at the METR plot
arXiv:2610.12466v1 Announce Type: new Abstract: METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpret…
- arXiv cs.AIresearchDiscovering Global False Negatives On the Fly for Self-supervised Contrastive Learning
arXiv:2502.20612v2 Announce Type: cross Abstract: In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, excluding the anchor.…
- arXiv cs.AIresearchSpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching
arXiv:2610.02660v1 Announce Type: cross Abstract: Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Transformer evaluations…
- arXiv cs.AIresearchFrom Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model
arXiv:2610.05711v1 Announce Type: cross Abstract: Strong image generation models are conditioned on class labels, aligned to frozen pretrained encoders, or built on separately trained autoencoders. While effective, gener…
- arXiv cs.AIresearchFreeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression
arXiv:2610.10552v1 Announce Type: cross Abstract: Comparing parameter-efficient fine-tuning recipes under a single, shared learning rate is a common but flawed practice: when the arms being compared have very different t…
- arXiv cs.AIresearchStrategic Governance of AI Models in Earth Science
arXiv:2610.10560v1 Announce Type: cross Abstract: AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their development and adop…
- arXiv cs.AIresearchSLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
arXiv:2610.10563v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textua…
- arXiv cs.AIresearchA Survey on LLM-Integrated Hardware Design Verification
arXiv:2610.10580v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into hardware verification to automate specification interpretation, verification-artifact generation, debu…
- arXiv cs.AIresearchCertified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
arXiv:2610.10597v1 Announce Type: cross Abstract: Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, selective disclosure of private variants, and bench…
- arXiv cs.AIagentsBeyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation
arXiv:2610.10604v1 Announce Type: cross Abstract: When generating verifiable code, natural language requirements are mapped to machine checked code using LLMs and agentic workflows. A crucial component of this pipeline i…
- arXiv cs.AIagentsFrom Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage
arXiv:2610.10608v1 Announce Type: cross Abstract: Security operations centers (SOCs) must triage large volumes of alerts, most of which are benign, while missed attacks can remain uninvestigated. Tool-using large languag…
- arXiv cs.AIagentsCode Understanding is a Bottleneck for Coding Agents
arXiv:2610.10610v1 Announce Type: cross Abstract: Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor control over code an…
- arXiv cs.AIresearchMRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
arXiv:2610.10617v1 Announce Type: cross Abstract: In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can ve…
- arXiv cs.AIagentsTestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution
arXiv:2610.10619v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all existing benchmarks still…
- arXiv cs.AIagentsWhen AI Finds Hidden Messages, Does It Report?
arXiv:2610.10620v1 Announce Type: cross Abstract: When an assistant encounters a message for another AI, does it tell its user? Four fixed model-provider deployments perform simulated source tasks in 1,280 ordinary-note…
- arXiv cs.AIresearchWorldBench: Evaluating LLMs on Three.js Voxel World Generation
arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges take one view of the ou…
- arXiv cs.AIresearchSAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understanding
arXiv:2610.10624v1 Announce Type: cross Abstract: Spatial audio-visual understanding requires models to recognize not only what is present, but also where events occur and how they relate across modalities. Existing benc…
- arXiv cs.AIagentsAgent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking
arXiv:2610.10628v1 Announce Type: cross Abstract: Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing…
- arXiv cs.AIresearchPhase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning
arXiv:2610.10630v1 Announce Type: cross Abstract: Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimensional classifier who…
- arXiv cs.AIresearchHas LLM Screening Performance Stalled in Software Engineering Systematic Reviews?
arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but LLMs are evolving r…
- arXiv cs.AIresearchVisible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation
arXiv:2610.10639v1 Announce Type: cross Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language ambiguity, schema groun…
- arXiv cs.AIresearchCoverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction
arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason…
- arXiv cs.AIresearchFrom Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier
arXiv:2610.10642v1 Announce Type: cross Abstract: This paper studies the construction of an explanatory space for a weighted naive Bayes classifier from the supervised representation induced by the model. We start from t…
- arXiv cs.AIresearchMasked Generative Motion Planning with Geometry-Guided Token Search
arXiv:2610.10646v1 Announce Type: cross Abstract: Generative motion planners typically use learned trajectory priors for initial generation, while leaving test-time repair to local continuous refinement. We introduce Mas…
- arXiv cs.AIresearchBeyond the Ergodic Wall: A Discrete Geometric Physics Sandbox for Analysing AI Scaling Limits and Complexity Collapse
arXiv:2610.10651v1 Announce Type: cross Abstract: This paper exposes the ergodic ceiling and thermodynamic inefficiency of current deep learning, which converges to a statistical average of historic human knowledge. True…