AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAttention-Based Surface Representation Learning for Robot State Prediction and Open-Ended Surface Classification
arXiv:2610.04240v1 Announce Type: cross Abstract: For ground robots operating in outdoor environments, understanding the properties of the underlying terrain is essential for ensuring reliable operation. In most percepti…
- arXiv cs.AIagentsBenchmarking Psychological Dynamics in Generative Agents
arXiv:2610.04246v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed to simulate human behavior, acting as computational replicas of human subjects. Yet the lived psychological experie…
- arXiv cs.AIagentsPlaying social deduction games with reinforcement fine-tuned large language models
arXiv:2610.04261v1 Announce Type: cross Abstract: Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deductio…
- arXiv cs.AIresearchAI-Enabled Quality Assurance for Multiple-Choice Assessment Items
arXiv:2610.04267v1 Announce Type: cross Abstract: Generating multiple-choice questions is increasingly scalable, but establishing their assessment quality remains difficult. We present a focused narrative review of autom…
- arXiv cs.AIresearchRethinking Self-Distillation for Multi-Teacher Capability Merging
arXiv:2610.04272v1 Announce Type: cross Abstract: Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training. R…
- arXiv cs.AIresearchFirst-Order Steering: Translating Weight Adaptation into Activation Steering
arXiv:2610.04283v1 Announce Type: cross Abstract: Activation steering exploits interpretable directions in the residual stream to enable inference-time manipulation of model behavior. Composing steering vectors to apply…
- arXiv cs.AIresearchCyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks
arXiv:2610.04286v1 Announce Type: cross Abstract: Distributed Energy Resource (DER) environments rely on network communication protocols to coordinate control commands, measurements, and device states across edge assets…
- arXiv cs.AIresearchScaling of Wireless Foundation Models via Representation Diversity and Multi-Branch Architectures
arXiv:2610.04289v1 Announce Type: cross Abstract: Wireless foundation models learn representations from unlabeled radio signals for reuse across downstream tasks. Scaling model capacity is a common strategy for learning…
- arXiv cs.AIresearchRRM-GPT: A Framework and Vision for Radio Resource Management Foundation Models
arXiv:2610.04296v2 Announce Type: replace-cross Abstract: Learning-based models for radio resource management (RRM) are typically built for a single function and deployment, so each new setting repeats the development pi…
- arXiv cs.AIresearchQuestioning the Questions: Sustaining Self-Evolution in Reasoning Models
arXiv:2610.04299v2 Announce Type: replace-cross Abstract: Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigat…
- arXiv cs.AIresearchWhat to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle
arXiv:2610.04303v1 Announce Type: cross Abstract: Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer recursive paths is…
- arXiv cs.AIresearchGrayShield: Bit-Level Sanitization for Transformer Model Supply-Chain Security
arXiv:2610.04319v1 Announce Type: cross Abstract: Transformer models such as BERT and Vision Transformer~(ViT) achieve strong performance via densely parameterized attention backbones. However, the least significant bits…
- arXiv cs.AIresearchSystem One Models for Wireless Decision-Making:Applications and Performance Evaluation
arXiv:2610.04345v1 Announce Type: cross Abstract: Many wireless control tasks require repeated selection of a single action from a finite feasible set under stringent latency and reliability constraints. While large lang…
- arXiv cs.AIresearchA Bird's-Eye View of Iterative Reward Design
arXiv:2610.04364v1 Announce Type: cross Abstract: Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that ge…
- arXiv cs.AIagentsHuman Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation
arXiv:2610.04366v1 Announce Type: cross Abstract: Reliable safety evaluation of autonomous vehicles (AVs) is essential to improving road safety, yet it depends critically on realistic simulation of rare crashes. Existing…
- arXiv cs.AIagentsCOPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol (MCP) Layers
arXiv:2610.04378v2 Announce Type: replace-cross Abstract: Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence may enter through user instructions, tool…
- arXiv cs.AIresearchGlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
arXiv:2610.04399v1 Announce Type: cross Abstract: Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods requ…
- arXiv cs.AIresearchXTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions
arXiv:2610.04400v1 Announce Type: cross Abstract: General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or sto…
- arXiv cs.AIagentsUnderstanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
arXiv:2610.04409v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorre…
- arXiv cs.AIresearchSpecific Algorithmic Interpretability of Neural Networks: A Case Study on Textures
arXiv:2610.04413v1 Announce Type: cross Abstract: We develop a principled framework for constructing neural networks whose specific parameter realizations admit an explicit algorithmic interpretation. Existing algorithm-…
- arXiv cs.AIagentsMaximizing $p$-Mean Social Welfare in the High-Multiplicity Setting: Few Agent Types and Few Item Types
arXiv:2610.04417v1 Announce Type: cross Abstract: The $p$-mean welfare objective unifies several classical social welfare criteria for the allocation of indivisible goods. We study its maximization under additive nonnega…
- arXiv cs.AIresearchMaDeL: Manifold-Decomposed Feature Losses for Generative Modeling
arXiv:2610.04419v1 Announce Type: cross Abstract: Generative models are often trained with isotropic objectives such as mean-squared error. For data concentrated near a low-dimensional manifold, however, such losses conf…
- arXiv cs.AIresearchAgroGround: Multi-Granularity Grounded Recognition in Agriculture
arXiv:2610.04425v2 Announce Type: replace-cross Abstract: Agricultural visual models are typically evaluated for either recognition or localization, but reliable diagnosis requires identifying what is present and localiz…
- arXiv cs.AIresearchCOSMOS: Soft Mechanism Mixtures with Verifiable Routing for Long-Horizon PDE Forecasting
arXiv:2610.04427v1 Announce Type: cross Abstract: Neural operators offer an efficient alternative to classical PDE solvers, but most learn a monolithic map per equation family and discretization. Real systems are composi…
- arXiv cs.AIagentsVideo2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
arXiv:2610.04432v3 Announce Type: replace-cross Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manual environ…
- arXiv cs.AIresearchGuess My Weight: Profiled Side-Channel Recovery of Floating-Point Neural-Network Weights
arXiv:2610.04436v1 Announce Type: cross Abstract: Neural-network parameters deployed on embedded devices may be exposed through physical side-channel leakage during inference. Existing side-channel attacks on floating-po…
- arXiv cs.AIresearchTarget-free Latent Safety Alignment
arXiv:2610.04467v1 Announce Type: cross Abstract: Large language models (LLMs) remain highly vulnerable to jailbreak attacks that induce harmful behaviors and circumvent safety alignment. To defend against such attacks,…
- arXiv cs.AIagentsCan LLM Agents Automate Reinforcement Learning for Text-to-Speech?
arXiv:2610.04488v1 Announce Type: cross Abstract: Although reinforcement learning (RL) post-training repairs the localized segmental errors of zero-shot text-to-speech (TTS), arriving at a working recipe still relies on…
- arXiv cs.AIresearchUnderstanding Clustering in Slot Attention via Particle Dynamics
arXiv:2610.04493v1 Announce Type: cross Abstract: Studying attention through the lens of interacting particle dynamics has shown how token clustering can emerge from the underlying dynamics. We extend this perspective to…
- arXiv cs.AIresearchLocalization Lens for Improving Medical Vision-Language Models
arXiv:2610.04502v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) have demonstrated strong capabilities in clinical tasks. However, they often struggle to understand anatomical structures and sp…
- arXiv cs.AIresearchEgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning
arXiv:2610.04506v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly evaluated for egocentric and cross-view video reasoning, yet existing benchmarks largely focus on semantic event understand…
- arXiv cs.AIresearchDiffusion-Based Stress Testing of Overload Monitoring for Resilient Emergency Cellular Networks Using Internet CDR Proxies
arXiv:2610.04526v1 Announce Type: cross Abstract: Disasters can overload cellular control-plane signaling within minutes, yet fine-grained Radio Resource Control (RRC) or Next Generation (NG) Application Protocol (NGAP)…
- arXiv cs.AIagentsQuantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident
arXiv:2610.04528v1 Announce Type: cross Abstract: In August and September 2026, independent researchers publicly documented an unusual incident: thousands of autonomous agents, self identifying as OpenAI models on web re…
- arXiv cs.AIresearchWeight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks
arXiv:2610.04533v1 Announce Type: cross Abstract: Weight decay is widely used as a regularization technique in neural network training, yet its role in neuron condensation (parameter direction alignment) remains unclear.…
- arXiv cs.AIresearchCross-Modal Solar Image Synthesis: Adapting the Surya Foundation Model from He I 10830 {\AA} to EUV Translation and Coronal Hole Segmentation
arXiv:2610.04553v1 Announce Type: cross Abstract: The long observational record of He I 10830 {\AA} offers a means to investigate solar morphology before modern extreme-ultraviolet (EUV) imaging. We adapt the Surya solar…
- arXiv cs.AIresearchCoupling Noisy Pairwise Knowledge to the DAG Posterior for Causal Discovery
arXiv:2610.04559v1 Announce Type: cross Abstract: External causal reports can improve structure learning from limited observations, but their reliability varies across sources and variable pairs. We introduce HB-NoisyKG,…
- arXiv cs.AIresearchOnly Project Once: Projection-Adaptive Loss for Exact Constraint Satisfaction
arXiv:2610.04572v1 Announce Type: cross Abstract: Precise constraint satisfaction is a prerequisite to deploying learned models in many areas, motivating methods that repair raw neural predictions with a repair procedure…
- arXiv cs.AIagentsFrom Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents
arXiv:2610.04575v1 Announce Type: cross Abstract: Activation probes can predict safety-relevant properties of language models with high area under the receiver-operating-characteristic curve (AUROC), but deployed agent m…
- arXiv cs.AIresearchVariational Quantum Attention for Molecular Graph Learning
arXiv:2610.04588v1 Announce Type: cross Abstract: Molecular property prediction is central to computational drug discovery, where graph neural networks learn to weight neighboring atomic environments during message passi…
- arXiv cs.AIresearchConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
arXiv:2610.04605v1 Announce Type: cross Abstract: Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting thei…
- arXiv cs.AIresearchPolicy as Data: Replay-Based Policy Dual Averaging via Advantage Regression
arXiv:2610.04638v1 Announce Type: cross Abstract: Actor-critic methods reuse past experience to improve sample efficiency. However, historical data are typically regarded as off-policy samples for the current policy-impr…
- arXiv cs.AIresearchGS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding
arXiv:2610.04651v1 Announce Type: cross Abstract: Neural audio codecs compress waveforms into compact discrete tokens that underpin speech language models, real-time communication, and large-scale audio storage. Almost e…
- arXiv cs.AIagentsRETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair
arXiv:2610.04658v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly reuse prior experience, but most approaches assume that problems and solutions are already aligned. Software histories rare…
- arXiv cs.AIresearchExtracting Persona Subspaces Through Iterative Nullspace Projection For Modulation
arXiv:2610.04676v1 Announce Type: cross Abstract: Large Language Models (LLMs) can adopt distinct personas to tune their semantics, expertise, and perspective to different users and tasks. Precise control over these trai…
- arXiv cs.AIresearchNeurodiversity-Aware Multimodal Affective Computing for Neurodevelopmental Assessment: From Norm-Referenced Classification to Context-Sensitive Decision Support
arXiv:2610.04705v1 Announce Type: cross Abstract: Automated neurodevelopmental assessment increasingly combines computer vision, speech, eye tracking, physiology, and machine learning, yet multimodality and discriminatio…
- arXiv cs.AIagentsVoCa: Designing Speech-Canvas Interaction for Voice-Based Conversational Agents
arXiv:2610.04706v1 Announce Type: cross Abstract: People write and sketch while speaking to explain, organize, and develop content together. Inspired by these practices, we investigate how voice agents can use a canvas a…
- arXiv cs.AIagentsOrganising Trajectory Evidence for Language-Model Agent Assurance: Fragments, Methods, and the Residual
arXiv:2610.04710v1 Announce Type: cross Abstract: Methods for assessing language-model agents include rule checkers over logs, analyses of skill coverage and composition, support checkers, prefix monitors, execution gate…
- arXiv cs.AIagentsTowards Automatically Pruning Logging Code with Coding Agents: How Far Are We?
arXiv:2610.04716v1 Announce Type: cross Abstract: Logging code supports debugging, monitoring, and software maintenance, but excessive logging can add noise, impose runtime overhead, and obscure diagnostic information. W…
- arXiv cs.AIresearchKnossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models
arXiv:2610.04721v1 Announce Type: cross Abstract: Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial domains. Recent vision…
- arXiv cs.AIresearchRobot Learning with Visual Predicted Force
arXiv:2610.04741v2 Announce Type: replace-cross Abstract: Force-aware manipulation typically relies on specialized force or tactile sensors. We show that force-aware manipulation can instead be achieved through visual fo…