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
HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment
arXiv cs.AI Research & Papers
AGI Maze as a Benchmark Framework for World-Modeling Agents
arXiv cs.AI Research & Papers
Coachable agents for interactive gameplay
arXiv cs.AI Research & Papers
Self-Evolving Agents with Anytime-Valid Certificates
arXiv cs.AI Research & Papers
Two AI Metrics Diverged: Will it Make All the Difference?
arXiv cs.AI Research & Papers
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation th…
arXiv cs.AI Research & Papers
Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on M…
arXiv cs.AI Research & Papers
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
arXiv cs.AI Research & Papers
AutoMem: Automated Learning of Memory as a Cognitive Skill
arXiv cs.AI Research & Papers
PedNStream: Scalable Network Flow Simulation for Pedestrian Traffic Management
arXiv cs.AI Research & Papers
Agentic generation of verifiable rules for deterministic, self-expanding reaction classif…
arXiv cs.AI Research & Papers
UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation acros…
arXiv cs.AI Research & Papers
DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching
arXiv cs.AI Research & Papers
From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extractio…
arXiv cs.AI Research & Papers
Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Voc…
arXiv cs.AI Research & Papers
BaRA: BFS-and-Reflection Web Data Collection Agent
arXiv cs.AI Research & Papers
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
arXiv cs.AI Research & Papers
Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Ob…
arXiv cs.AI Research & Papers
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval …
arXiv cs.AI Research & Papers
GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lig…
arXiv cs.AI Research & Papers
Towards an automated AI-based framework for floor plan compliance checks for residential …
arXiv cs.AI Research & Papers
LLMs in the Real World: Evaluating "AI" in Emergency Contexts
arXiv cs.AI Research & Papers
Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders
arXiv cs.AI Research & Papers
Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention
arXiv cs.AI Research & Papers
Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration
arXiv cs.AI Research & Papers
ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis
arXiv cs.AI Research & Papers
Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study
arXiv cs.AI Research & Papers
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
arXiv cs.AI Research & Papers
Active Sensing for RIS-Aided Tracking and Power Control: A Hybrid Neuroevolution and Supe…
arXiv cs.AI Research & Papers
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning