Español

Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
Efficient Test-time Inference for Generative Planning Models
arXiv cs.AI Research & Papers
ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment
arXiv cs.AI Research & Papers
AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Verifiable Mathematical Re…
arXiv cs.AI Research & Papers
An Abstract Worlds Semantic Framework for Belief Change Operators
arXiv cs.AI Research & Papers
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
arXiv cs.AI Research & Papers
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
arXiv cs.AI Research & Papers
LLM-Driven Co-Evolutionary Automated Heuristic Design for Bi-Component Coupled Combinator…
arXiv cs.AI Research & Papers
AI Sovereignty as National Learning Capacity: A Human-Centered Learning Mechanics Viewpoi…
arXiv cs.AI Research & Papers
Interaction-Centered Intelligence: Toward Interaction as the Primary Unit of Analysis in …
arXiv cs.AI Research & Papers
DarkVesselNet: Multi-Modal Remote Sensing and Trajectory Reasoning for Dark Vessel Detect…
arXiv cs.AI Research & Papers
Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults
arXiv cs.AI Research & Papers
Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specificati…
arXiv cs.AI Research & Papers
Large Language Models in Transportation Systems Management and Operations: From Text Reas…
arXiv cs.AI Research & Papers
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Info…
arXiv cs.AI Research & Papers
Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Subm…
arXiv cs.AI Research & Papers
TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
arXiv cs.AI Research & Papers
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
arXiv cs.AI Research & Papers
Before the Model Learns the Bug:Fuzzing RLVR Verifiers
arXiv cs.AI Research & Papers
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
arXiv cs.AI Research & Papers
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
arXiv cs.AI Research & Papers
"Skill issues'': data-centric optimization of lakehouse agents
arXiv cs.AI Research & Papers
The Case for Model Science: Verify, Explore, Steer, Refine
arXiv cs.AI Research & Papers
The Shape of Wisdom: Decision Trajectories in Language Models
arXiv cs.AI Research & Papers
Brain-Atlas-Guided Generative Counterfactual Attention for Explainable Cognitive Decline …
arXiv cs.AI Research & Papers
SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback
arXiv cs.AI Research & Papers
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
arXiv cs.AI Research & Papers
Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery
arXiv cs.AI Research & Papers
FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized…
arXiv cs.AI Research & Papers
GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning
arXiv cs.AI Research & Papers
Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resoluti…