Home/Feed archiveFeed archiveAI news of 19 October 2026: every article19 October 2026 · 200 articles · Read the morning edition of 19 October 2026Every article published on 19 October 2026, from the most recent to the oldest.23:48Fossil fuels make a comeback in the USBusiness & StrategyAI | The Verge7/10Relevance 7 out of 1023:28CoreWeave's debt becomes the whole AI industry's problemBusiness & StrategyAI | The Verge8/10Relevance 8 out of 1023:14Amazon SageMaker JumpStart 2026 mid-year review: 100+ models onboardedTools & ProductsArtificial Intelligence8/10Relevance 8 out of 1022:09Amazon launches TorchNeuron to challenge Nvidia on PyTorchDev & DataAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 1021:39Top storyPSA: Patch your Plex media server before critical flaws are exploitedEthics & RegulationBiz & IT - Ars Technica8/10Relevance 8 out of 1021:28Hackers target OpenCode, AI coding tool, racking up charges on users' accountsDev & DataAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 1021:18Muse Spark Open outperforms Mistral Large 4 on benchmark, but loses on agent tasksResearch & ScienceActuIA8/10Relevance 8 out of 1021:00Tolan raises $30M for its AI companion app helping users navigate lifeTools & ProductsAI News & Artificial Intelligence | TechCrunch7/10Relevance 7 out of 1020:49Replika’s founder launches Wabi, a free personal AI assistantTools & ProductsAI News & Artificial Intelligence | TechCrunch7/10Relevance 7 out of 1020:37Tenstorrent raises $1.5B at $6.2B valuation to challenge NvidiaHardware & InfraAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 1020:30ReactOS now supports NTFS installationDev & DataBiz & IT - Ars Technica7/10Relevance 7 out of 1020:22MiniMax M3.1 Flash: New low-cost AI model from China challenges pricingBig Tech & IndustryThe Decoder8/10Relevance 8 out of 1019:36Kling AI launches version 4.0 with stereo audio and multilingual lip syncTools & ProductsThe Decoder7/10Relevance 7 out of 1018:49TwelveLabs Pegasus 1.5 now available on Amazon BedrockTools & ProductsArtificial Intelligence8/10Relevance 8 out of 1018:23Deepgram optimizes voice AI with AWS Trainium for batch inferenceHardware & InfraArtificial Intelligence8/10Relevance 8 out of 1018:13Users turn to AI to strip down their smart TVsAgents & AutomationAI News & Artificial Intelligence | TechCrunch7/10Relevance 7 out of 1018:05Push-based KV transfer to improve TTFT and TPOT in vLLMDev & DataArtificial Intelligence8/10Relevance 8 out of 1018:03Optimizing TTFT for multi-turn agentic workloads with bidirectional KV transfer in vLLMDev & DataArtificial Intelligence8/10Relevance 8 out of 1017:37Nvidia launches open models for enterprise and on-device AI agentsBig Tech & IndustryAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 1016:30JB Pritzker: AI could extend life or threaten us like nuclear weaponsBusiness & StrategyAI | The Verge7/10Relevance 7 out of 1016:06G7 selects S3NS's SecNumCloud for sensitive data storageHardware & InfraActualités intelligence-artificielle8/10Relevance 8 out of 1015:58Top storyHacker uses AI agents to breach John Deere, SharkNinja and othersEthics & RegulationAI | The Verge8/10Relevance 8 out of 1015:55Google increases website visibility in AI search responsesBig Tech & IndustrySiècle Digital8/10Relevance 8 out of 1015:49MYM under Arcom investigation for minors' access to adult contentEthics & RegulationSiècle Digital7/10Relevance 7 out of 1015:44Anthropic proposes legal framework to block dangerous AI in the USEthics & RegulationSiècle Digital8/10Relevance 8 out of 1015:37Meta backs down on using web content to train its AIBig Tech & IndustrySiècle Digital8/10Relevance 8 out of 1015:20OpenAI is developing a humanoid robot to operate in the real worldBig Tech & IndustrySiècle Digital8/10Relevance 8 out of 1015:10Fraud refunds: EU court forces banks to reimburse firstBusiness & StrategySiècle Digital8/10Relevance 8 out of 1014:51Stripe sees rise in AI agent purchases but won’t disclose numbersBusiness & StrategyThe Decoder7/10Relevance 7 out of 1014:30Laplace Intelligence stress-tests robots and self-driving cars in simulation before deploymentAgents & AutomationAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 1014:14Cybersecurity: France's critical infrastructures struggle with automated attack responseEthics & RegulationActualités intelligence-artificielle8/10Relevance 8 out of 1014:00Democrats push for AI crackdown to gain midterm advantageBusiness & StrategyAI | The Verge7/10Relevance 7 out of 1014:00OpenAI enhances ChatGPT for low-resource programming languagesDev & DataOpenAI News8/10Relevance 8 out of 1013:33The neocloud shakeout is coming, and Nvidia has the most to loseBig Tech & IndustryThe Decoder8/10Relevance 8 out of 1013:19Anthropic proposes strict thresholds to block an AI modelEthics & RegulationActuIA8/10Relevance 8 out of 1013:19Anthropic creates fund for workers threatened by AIBusiness & StrategyThe Decoder8/10Relevance 8 out of 1013:03French Tech 2030: 80 startups selected for 2026 cohortBusiness & StrategyActualités intelligence-artificielle7/10Relevance 7 out of 1011:18Italy: AI cannot alone decide on firing or sanctions from October 2026Ethics & RegulationActuIA9/10Relevance 9 out of 1006:00Moral sycophancy in vision-language modelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00New model for multi-channel time series forecasting using sparse attentionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Towards reliable truth-aligned uncertainty estimation in large language modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Detecting multi-agent collusion via multi-agent interpretabilityResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00NEXUS: Safe planning for embodied agents with learned safety constraintsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure GenerationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Brain Vascular Age Prediction Using Cerebral Blood Flow and AIResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP OverridesAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00New approach for adaptive user representations using diffusion modelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00ERS: Hierarchical reasoning system based on explicit state graphsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00ECHOES: Recursive History Compression for Long-Horizon GUI AgentsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological ModelResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00PRIME: Method for verifiable reasoning in LLM agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Hierarchical feedback-guided LLM planning for executable control in cyber-physical systemsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Null controls are necessary but insufficient for scientific AI discoveryResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00L-SplineFNO: Neural Operator for Irregular Meshes in EngineeringResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Functional welfare of AI as a safety concernResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00An AI agent for auditing reproducibility in conference papersResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Harness-Delta Attribution: Dissecting Gains From Harness EvolutionResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LLM-based agents fail formal planning validation in most casesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Are Large Reasoning Models Good for Everyday Reasoning?Research & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00FRACTAL: A self-similar multi-agent orchestration architecture with formal boundsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Repairing LLM-generated specifications with deterministic diagnosisResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Autonomous AI Discovery at the Limits of Computability: Pushing the Busy Beaver FrontierResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00QEMem: A framework to enhance memory utilization in LLM agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00TAG-Nav: A task-agnostic framework for mobile GUI navigation with graph memoryAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00FlexUMM: Flexible Representation Learning for Unified Multimodal ModelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Contradictory effects of verifier feedback in formal theorem provingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Brain-aligned multimodal LLMs for emotional understanding in cartoonsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00GlobeBench: Benchmarking Text-Based World Models for Scalable SimulationsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LEMON: Zero-shot misbehavior monitoring for new LLMs without retrainingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Impact of graph serialization on reasoning LLMsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00R²Orch: Recursive Self-Improvement for Agent Orchestration via Self-PlayAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Avoiding Over-Specification in Coding BenchmarksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution MarginBusiness & Strategycs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00When Can You Trust an Agent's Own Verifier? Testing AI Agent Verifiers Under Optimization PressureResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Reward models: harmful generalization after targeted fine-tuningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00WAC Model: Joint Foresight and Criticism for Policy LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Evo-B&B: AI-guided evolutionary framework for branching policies in MILPResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00MS-Eval: Evaluating Sub-Agent Delegation in MCP-Intensive ScenariosAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00ShadowFPT: Backdooring Federated Prompt Tuning via Shadow TriggersResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Real-time error correction for time series forecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00ToPA: Block-wise Toeplitz Adaptation for Efficient Fine-TuningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00When to forget: risk-controlled context adaptation for long-horizon agentsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool AgentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Sep-Latent: Separator Tokens for Optimizing Implicit Reasoning in LLMsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Effective-Horizon Compression in Multi-Turn JailbreaksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00DiffusionRVGE: Value Gradient Estimation via Regression for Reinforcement Learning in Diffusion ModelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Privilege Escalation Attacks on Harness-Protected Coding AgentsEthics & Regulationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00GOLD: Geometric Optimized Latent Diffusion for RNA Structure-Aware Inverse FoldingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00CPU-GPU collaborative MoE inference system for efficient executionResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00New framework for adapting computer-use agents using user manualsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Causal Attribution of Marketing Labels in AI-Generated AdsBusiness & Strategycs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00ASE: A modular framework to integrate text in time series forecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Actionable research limitations: forward-citation supervision for automated ideationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Lost Performance: Analyzing and Fixing C-to-Rust Translation RegressionsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RLResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?Research & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Improving GRPO for safety alignment in large reasoning modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00WebCoder: An AI agent for general frontend developmentAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LexPilot: Benchmarking Proactive Interaction of Legal LLMs with Laypeople in Chinese Civil CasesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00CIIR: Class-Indexed Interface Representation LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00QuAD: Quantitative assessment of qualitative data quality via distribution alignmentResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Algorithm Modelization: Turning algorithms into evolvable modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LongForge: Improving long-context instruction data via evidence-assertion reasoning graphsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00OfficeTown: A simulation framework for evolving professional agent intelligenceAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00FuzzInsight: Optimizing the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN FuzzingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Extra test-time compute doesn't always add evidence in LLM reasoningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Conceptual framework for analyzing RAG techniquesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00PrefMind: Online multi-agent preference learning for multimodal response generationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Reasoning models control their chains of thought via self-instructionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Annotrace: A tool for step-level annotation of AI agent tracesTools & Productscs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00CoTA++: Solving the Repeat Curse in Diffusion-based Multimodal LLMsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Optimist Deep Research: An autonomous agent for iterative literature researchAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00SimOPD: Relational Knowledge Transfer for On-Policy DistillationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00SRCoT: Evidence-Based Text Generation via a Closed Retrieve--Reflect--Revise Loop for Edge LLMsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00MemCompile: A framework for compiling long-term agent memoriesAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00AgentOnto: Ontology-Guided LLM Agents for Enterprise Data AnalyticsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Robust AI agent tool use despite changing interfacesAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series ForecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00LLM Monitor Validity Failures: Security Evidence Path IssuesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Improving Generative Policies from Observational DataResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00ScoutRoute: Efficient MoE Routing via Internal Model SignalsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00GatewayBench: Evaluation platform for MCP gatewaysAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00S-GAP: Stealthy Attacks on GraphLLMs via Unified PrimitivesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LocalIntent: Outcome-Specific Structured Generation for Smart Building Automation with Local LLMsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Evaluating Narrative-Induced Sycophancy in Large Language ModelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00SkillBrowser: Dynamic skill management for AI agentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Darwin-Claw: Adaptive self-evolution framework for autonomous agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00New retrieval framework improves long-term memory for AI agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Cognitive differentiation of skills for self-improving agentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00GEMS: Molecular Structure Identification via Guided Search over Isomer GraphsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00OwlSight: A Chain-of-Thought Reasoning MonitorResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00A new framework to model mental states and their evolutionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00DrugHarness: An Evolvable Agent System for Computational Drug DiscoveryAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper GPUsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Consistent Concept Discovery with Sparse Coding Beyond SAEsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Self-building labs speed up scientific researchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00AI agents for automating reproducibility in medical researchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00CausalEvo: Causal Skill Self-Evolution for Health LLM AgentsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Can LLMs effectively calibrate engineering simulators under budget constraints?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Interactive clarification to improve Lean formal specificationsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Generative agents for real-aligned urban mobility simulationsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Evaluating explainable harmonic decision-making on music corporaResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00M2CG: A Non-Recursive Approach for Medical Image AlignmentResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00LLM Safety Evaluation: A Bias Linked to Query FormResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00TRACE: Efficient Transformer Residual Activation Encoding for Distributed Edge InferenceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Sparse Autoencoders to Mitigate Catastrophic Forgetting in Continual LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00DriveWorld3D: 3D World Modeling with Evidence Constraints for Autonomous DrivingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Analysis of political narratives during Moldova's 2024 presidential electionResearch & Sciencecs.AI updates on arXiv.org7/10Relevance 7 out of 1006:00Recursive self-distillation risks progressive misalignment in AI modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Upper bounds on the number of causal pieces in spiking neural networksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00AuditKIT: A unified evaluation spine for benchmarking LLMs and agentic systemsDev & Datacs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Mitigating demographic disparities in explanation fairness for hate speech moderationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Can LLMs predict the outcomes of machine learning experiments?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Tree-species recognition with LiDAR: limited cross-source generalization revealedResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00StratFL: New defense against model poisoning attacks in federated learningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Freeway speed forecasting with sparse sensors using graph networksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Plausible explanations mislead multimodal AI judgesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00ToMStories: Evaluating Theory of Mind in Language ModelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00New method to measure LLM uncertainty through causal robustnessResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00On-Demand Hard Instances for Algorithm EvaluationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Diverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for RL ExplorationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00AlphaBet: Reinforcement Learning for LLM Event Forecasting AgentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00BRIA: AI agent for selective tool use in large librariesAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00NoveltyScope: Multi-agent research assistant for novelty assessment of scientific papersResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00ARBOR: Detecting reasoning failures in long chains of thoughtResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00OrderFlowDiT: Diffusion Transformer for Limit-Order Volume ForecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00CADENCE: Adaptive decoding method to speed up text generationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Self-evolving coding agents through recursive optimizationAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Reducing private data leakage in fine-tuned LLMs via neuron pruningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00STRIDE: New benchmark for spatiotemporal reasoning in autonomous drivingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level FallsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00AnchorQ: Efficient Policy Improvement for Robotics via Structured Latent Action AnchorsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00New budget allocation method for optimizing LLM tree searchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LLM agents in collective-risk dilemmas: limited adaptabilityResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Learning to Be Guided: Optimizing Latent Geometry for Classifier-Free GuidanceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00RLVR: Are long rollout windows really necessary?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Competence-based evaluation of logical reasoning in large language modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00HAPACT: A benchmark for localizing physical impacts on the human body in videosResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00COMET: Method for Continual Vision-Language LearningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Same Attention Circuit Drives Multiple Post-Training BiasesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Aligning Language Models for Counterfactual InvarianceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00NL2SQL via iterative self-refinement with specialized agentsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Prism Attention: Efficient KV-Cache Sharing for Long-Context LLM InferenceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00PersonaCUABench: Evaluating computer-use agents based on user personasResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Noise-robust algorithm for graph data labelingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural NetworksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Unifying Embodied Foundation Models via a Model-to-Policy FormulationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Relational models trained on synthetic data for graph databasesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Local proxies for memory-efficient neural trainingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00AI models struggle to explain chess and Go moves in natural languageResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00HyperPersona: A hypergraph framework for text-based personality predictionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Strategies for simulator recalibration under data driftResearch & Sciencecs.AI updates on arXiv.org7/10Relevance 7 out of 1006:00Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00MoEvolve: A distillation method to strengthen MoE modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial OptimizationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00Hierarchical model of perceptual learning for spatial hearing based on free energy principleResearch & Sciencecs.AI updates on arXiv.org7/10Relevance 7 out of 1006:00Validating AI-generated political networks against survey dataResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 1006:00qGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision AcceleratorsHardware & Infracs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00MGE-PO: Entropy-Aware Credit Assignment for Mathematical ReasoningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 1006:00Agentic AI system prevents data hallucinations in optical network troubleshootingAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10All feed archivesPrevious day: 18 October 2026Next day: 20 October 2026
23:48Fossil fuels make a comeback in the USBusiness & StrategyAI | The Verge7/10Relevance 7 out of 10
23:28CoreWeave's debt becomes the whole AI industry's problemBusiness & StrategyAI | The Verge8/10Relevance 8 out of 10
23:14Amazon SageMaker JumpStart 2026 mid-year review: 100+ models onboardedTools & ProductsArtificial Intelligence8/10Relevance 8 out of 10
22:09Amazon launches TorchNeuron to challenge Nvidia on PyTorchDev & DataAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 10
21:39Top storyPSA: Patch your Plex media server before critical flaws are exploitedEthics & RegulationBiz & IT - Ars Technica8/10Relevance 8 out of 10
21:28Hackers target OpenCode, AI coding tool, racking up charges on users' accountsDev & DataAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 10
21:18Muse Spark Open outperforms Mistral Large 4 on benchmark, but loses on agent tasksResearch & ScienceActuIA8/10Relevance 8 out of 10
21:00Tolan raises $30M for its AI companion app helping users navigate lifeTools & ProductsAI News & Artificial Intelligence | TechCrunch7/10Relevance 7 out of 10
20:49Replika’s founder launches Wabi, a free personal AI assistantTools & ProductsAI News & Artificial Intelligence | TechCrunch7/10Relevance 7 out of 10
20:37Tenstorrent raises $1.5B at $6.2B valuation to challenge NvidiaHardware & InfraAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 10
20:30ReactOS now supports NTFS installationDev & DataBiz & IT - Ars Technica7/10Relevance 7 out of 10
20:22MiniMax M3.1 Flash: New low-cost AI model from China challenges pricingBig Tech & IndustryThe Decoder8/10Relevance 8 out of 10
19:36Kling AI launches version 4.0 with stereo audio and multilingual lip syncTools & ProductsThe Decoder7/10Relevance 7 out of 10
18:49TwelveLabs Pegasus 1.5 now available on Amazon BedrockTools & ProductsArtificial Intelligence8/10Relevance 8 out of 10
18:23Deepgram optimizes voice AI with AWS Trainium for batch inferenceHardware & InfraArtificial Intelligence8/10Relevance 8 out of 10
18:13Users turn to AI to strip down their smart TVsAgents & AutomationAI News & Artificial Intelligence | TechCrunch7/10Relevance 7 out of 10
18:05Push-based KV transfer to improve TTFT and TPOT in vLLMDev & DataArtificial Intelligence8/10Relevance 8 out of 10
18:03Optimizing TTFT for multi-turn agentic workloads with bidirectional KV transfer in vLLMDev & DataArtificial Intelligence8/10Relevance 8 out of 10
17:37Nvidia launches open models for enterprise and on-device AI agentsBig Tech & IndustryAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 10
16:30JB Pritzker: AI could extend life or threaten us like nuclear weaponsBusiness & StrategyAI | The Verge7/10Relevance 7 out of 10
16:06G7 selects S3NS's SecNumCloud for sensitive data storageHardware & InfraActualités intelligence-artificielle8/10Relevance 8 out of 10
15:58Top storyHacker uses AI agents to breach John Deere, SharkNinja and othersEthics & RegulationAI | The Verge8/10Relevance 8 out of 10
15:55Google increases website visibility in AI search responsesBig Tech & IndustrySiècle Digital8/10Relevance 8 out of 10
15:49MYM under Arcom investigation for minors' access to adult contentEthics & RegulationSiècle Digital7/10Relevance 7 out of 10
15:44Anthropic proposes legal framework to block dangerous AI in the USEthics & RegulationSiècle Digital8/10Relevance 8 out of 10
15:37Meta backs down on using web content to train its AIBig Tech & IndustrySiècle Digital8/10Relevance 8 out of 10
15:20OpenAI is developing a humanoid robot to operate in the real worldBig Tech & IndustrySiècle Digital8/10Relevance 8 out of 10
15:10Fraud refunds: EU court forces banks to reimburse firstBusiness & StrategySiècle Digital8/10Relevance 8 out of 10
14:51Stripe sees rise in AI agent purchases but won’t disclose numbersBusiness & StrategyThe Decoder7/10Relevance 7 out of 10
14:30Laplace Intelligence stress-tests robots and self-driving cars in simulation before deploymentAgents & AutomationAI News & Artificial Intelligence | TechCrunch8/10Relevance 8 out of 10
14:14Cybersecurity: France's critical infrastructures struggle with automated attack responseEthics & RegulationActualités intelligence-artificielle8/10Relevance 8 out of 10
14:00Democrats push for AI crackdown to gain midterm advantageBusiness & StrategyAI | The Verge7/10Relevance 7 out of 10
14:00OpenAI enhances ChatGPT for low-resource programming languagesDev & DataOpenAI News8/10Relevance 8 out of 10
13:33The neocloud shakeout is coming, and Nvidia has the most to loseBig Tech & IndustryThe Decoder8/10Relevance 8 out of 10
13:19Anthropic proposes strict thresholds to block an AI modelEthics & RegulationActuIA8/10Relevance 8 out of 10
13:19Anthropic creates fund for workers threatened by AIBusiness & StrategyThe Decoder8/10Relevance 8 out of 10
13:03French Tech 2030: 80 startups selected for 2026 cohortBusiness & StrategyActualités intelligence-artificielle7/10Relevance 7 out of 10
11:18Italy: AI cannot alone decide on firing or sanctions from October 2026Ethics & RegulationActuIA9/10Relevance 9 out of 10
06:00Moral sycophancy in vision-language modelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00New model for multi-channel time series forecasting using sparse attentionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Towards reliable truth-aligned uncertainty estimation in large language modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Detecting multi-agent collusion via multi-agent interpretabilityResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00NEXUS: Safe planning for embodied agents with learned safety constraintsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure GenerationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Brain Vascular Age Prediction Using Cerebral Blood Flow and AIResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP OverridesAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00New approach for adaptive user representations using diffusion modelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ERS: Hierarchical reasoning system based on explicit state graphsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ECHOES: Recursive History Compression for Long-Horizon GUI AgentsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological ModelResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00PRIME: Method for verifiable reasoning in LLM agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Hierarchical feedback-guided LLM planning for executable control in cyber-physical systemsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Null controls are necessary but insufficient for scientific AI discoveryResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00L-SplineFNO: Neural Operator for Irregular Meshes in EngineeringResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Functional welfare of AI as a safety concernResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00An AI agent for auditing reproducibility in conference papersResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Harness-Delta Attribution: Dissecting Gains From Harness EvolutionResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LLM-based agents fail formal planning validation in most casesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Are Large Reasoning Models Good for Everyday Reasoning?Research & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00FRACTAL: A self-similar multi-agent orchestration architecture with formal boundsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Repairing LLM-generated specifications with deterministic diagnosisResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Autonomous AI Discovery at the Limits of Computability: Pushing the Busy Beaver FrontierResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00QEMem: A framework to enhance memory utilization in LLM agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00TAG-Nav: A task-agnostic framework for mobile GUI navigation with graph memoryAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00FlexUMM: Flexible Representation Learning for Unified Multimodal ModelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Contradictory effects of verifier feedback in formal theorem provingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Brain-aligned multimodal LLMs for emotional understanding in cartoonsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00GlobeBench: Benchmarking Text-Based World Models for Scalable SimulationsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LEMON: Zero-shot misbehavior monitoring for new LLMs without retrainingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Impact of graph serialization on reasoning LLMsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00R²Orch: Recursive Self-Improvement for Agent Orchestration via Self-PlayAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Avoiding Over-Specification in Coding BenchmarksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution MarginBusiness & Strategycs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00When Can You Trust an Agent's Own Verifier? Testing AI Agent Verifiers Under Optimization PressureResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Reward models: harmful generalization after targeted fine-tuningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00WAC Model: Joint Foresight and Criticism for Policy LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Evo-B&B: AI-guided evolutionary framework for branching policies in MILPResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00MS-Eval: Evaluating Sub-Agent Delegation in MCP-Intensive ScenariosAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00ShadowFPT: Backdooring Federated Prompt Tuning via Shadow TriggersResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Real-time error correction for time series forecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ToPA: Block-wise Toeplitz Adaptation for Efficient Fine-TuningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00When to forget: risk-controlled context adaptation for long-horizon agentsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool AgentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Sep-Latent: Separator Tokens for Optimizing Implicit Reasoning in LLMsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Effective-Horizon Compression in Multi-Turn JailbreaksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00DiffusionRVGE: Value Gradient Estimation via Regression for Reinforcement Learning in Diffusion ModelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Privilege Escalation Attacks on Harness-Protected Coding AgentsEthics & Regulationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00GOLD: Geometric Optimized Latent Diffusion for RNA Structure-Aware Inverse FoldingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00CPU-GPU collaborative MoE inference system for efficient executionResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00New framework for adapting computer-use agents using user manualsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Causal Attribution of Marketing Labels in AI-Generated AdsBusiness & Strategycs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ASE: A modular framework to integrate text in time series forecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Actionable research limitations: forward-citation supervision for automated ideationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Lost Performance: Analyzing and Fixing C-to-Rust Translation RegressionsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RLResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?Research & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Improving GRPO for safety alignment in large reasoning modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00WebCoder: An AI agent for general frontend developmentAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LexPilot: Benchmarking Proactive Interaction of Legal LLMs with Laypeople in Chinese Civil CasesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00CIIR: Class-Indexed Interface Representation LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00QuAD: Quantitative assessment of qualitative data quality via distribution alignmentResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Algorithm Modelization: Turning algorithms into evolvable modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LongForge: Improving long-context instruction data via evidence-assertion reasoning graphsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00OfficeTown: A simulation framework for evolving professional agent intelligenceAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00FuzzInsight: Optimizing the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN FuzzingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Extra test-time compute doesn't always add evidence in LLM reasoningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Conceptual framework for analyzing RAG techniquesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00PrefMind: Online multi-agent preference learning for multimodal response generationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Reasoning models control their chains of thought via self-instructionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Annotrace: A tool for step-level annotation of AI agent tracesTools & Productscs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00CoTA++: Solving the Repeat Curse in Diffusion-based Multimodal LLMsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Optimist Deep Research: An autonomous agent for iterative literature researchAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00SimOPD: Relational Knowledge Transfer for On-Policy DistillationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00SRCoT: Evidence-Based Text Generation via a Closed Retrieve--Reflect--Revise Loop for Edge LLMsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00MemCompile: A framework for compiling long-term agent memoriesAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00AgentOnto: Ontology-Guided LLM Agents for Enterprise Data AnalyticsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Robust AI agent tool use despite changing interfacesAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series ForecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00LLM Monitor Validity Failures: Security Evidence Path IssuesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Improving Generative Policies from Observational DataResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ScoutRoute: Efficient MoE Routing via Internal Model SignalsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00GatewayBench: Evaluation platform for MCP gatewaysAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00S-GAP: Stealthy Attacks on GraphLLMs via Unified PrimitivesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LocalIntent: Outcome-Specific Structured Generation for Smart Building Automation with Local LLMsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Evaluating Narrative-Induced Sycophancy in Large Language ModelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00SkillBrowser: Dynamic skill management for AI agentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Darwin-Claw: Adaptive self-evolution framework for autonomous agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00New retrieval framework improves long-term memory for AI agentsAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Cognitive differentiation of skills for self-improving agentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00GEMS: Molecular Structure Identification via Guided Search over Isomer GraphsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00OwlSight: A Chain-of-Thought Reasoning MonitorResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00A new framework to model mental states and their evolutionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00DrugHarness: An Evolvable Agent System for Computational Drug DiscoveryAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper GPUsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Consistent Concept Discovery with Sparse Coding Beyond SAEsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Self-building labs speed up scientific researchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00AI agents for automating reproducibility in medical researchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00CausalEvo: Causal Skill Self-Evolution for Health LLM AgentsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Can LLMs effectively calibrate engineering simulators under budget constraints?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Interactive clarification to improve Lean formal specificationsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Generative agents for real-aligned urban mobility simulationsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Evaluating explainable harmonic decision-making on music corporaResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00M2CG: A Non-Recursive Approach for Medical Image AlignmentResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00LLM Safety Evaluation: A Bias Linked to Query FormResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00TRACE: Efficient Transformer Residual Activation Encoding for Distributed Edge InferenceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Sparse Autoencoders to Mitigate Catastrophic Forgetting in Continual LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00DriveWorld3D: 3D World Modeling with Evidence Constraints for Autonomous DrivingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Analysis of political narratives during Moldova's 2024 presidential electionResearch & Sciencecs.AI updates on arXiv.org7/10Relevance 7 out of 10
06:00Recursive self-distillation risks progressive misalignment in AI modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Upper bounds on the number of causal pieces in spiking neural networksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00AuditKIT: A unified evaluation spine for benchmarking LLMs and agentic systemsDev & Datacs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Mitigating demographic disparities in explanation fairness for hate speech moderationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Can LLMs predict the outcomes of machine learning experiments?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Tree-species recognition with LiDAR: limited cross-source generalization revealedResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00StratFL: New defense against model poisoning attacks in federated learningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Freeway speed forecasting with sparse sensors using graph networksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Plausible explanations mislead multimodal AI judgesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00ToMStories: Evaluating Theory of Mind in Language ModelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00New method to measure LLM uncertainty through causal robustnessResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00On-Demand Hard Instances for Algorithm EvaluationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Diverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for RL ExplorationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00AlphaBet: Reinforcement Learning for LLM Event Forecasting AgentsAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00BRIA: AI agent for selective tool use in large librariesAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00NoveltyScope: Multi-agent research assistant for novelty assessment of scientific papersResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ARBOR: Detecting reasoning failures in long chains of thoughtResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00OrderFlowDiT: Diffusion Transformer for Limit-Order Volume ForecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00CADENCE: Adaptive decoding method to speed up text generationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Self-evolving coding agents through recursive optimizationAgents & Automationcs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Reducing private data leakage in fine-tuned LLMs via neuron pruningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00STRIDE: New benchmark for spatiotemporal reasoning in autonomous drivingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level FallsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00AnchorQ: Efficient Policy Improvement for Robotics via Structured Latent Action AnchorsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00New budget allocation method for optimizing LLM tree searchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LLM agents in collective-risk dilemmas: limited adaptabilityResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Learning to Be Guided: Optimizing Latent Geometry for Classifier-Free GuidanceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00RLVR: Are long rollout windows really necessary?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Competence-based evaluation of logical reasoning in large language modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00HAPACT: A benchmark for localizing physical impacts on the human body in videosResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00COMET: Method for Continual Vision-Language LearningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Same Attention Circuit Drives Multiple Post-Training BiasesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Aligning Language Models for Counterfactual InvarianceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00NL2SQL via iterative self-refinement with specialized agentsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Prism Attention: Efficient KV-Cache Sharing for Long-Context LLM InferenceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00PersonaCUABench: Evaluating computer-use agents based on user personasResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Noise-robust algorithm for graph data labelingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural NetworksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Unifying Embodied Foundation Models via a Model-to-Policy FormulationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Relational models trained on synthetic data for graph databasesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Local proxies for memory-efficient neural trainingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00AI models struggle to explain chess and Go moves in natural languageResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00HyperPersona: A hypergraph framework for text-based personality predictionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Strategies for simulator recalibration under data driftResearch & Sciencecs.AI updates on arXiv.org7/10Relevance 7 out of 10
06:00Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement LearningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00MoEvolve: A distillation method to strengthen MoE modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial OptimizationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Hierarchical model of perceptual learning for spatial hearing based on free energy principleResearch & Sciencecs.AI updates on arXiv.org7/10Relevance 7 out of 10
06:00Validating AI-generated political networks against survey dataResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00qGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision AcceleratorsHardware & Infracs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00MGE-PO: Entropy-Aware Credit Assignment for Mathematical ReasoningResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Agentic AI system prevents data hallucinations in optical network troubleshootingAgents & Automationcs.AI updates on arXiv.org8/10Relevance 8 out of 10