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
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
arXiv cs.AI Research & Papers
AI Companions as Hyper Attachment and Caregiving Targets
arXiv cs.AI Research & Papers
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
arXiv cs.AI Research & Papers
ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph
arXiv cs.AI Research & Papers
Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training
arXiv cs.AI Research & Papers
Intent-Governed Tool Authorization for AI Agents
arXiv cs.AI Research & Papers
Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual …
arXiv cs.AI Research & Papers
Holmes: Multimodal Agentic Diagnosis for Mixed-Language Mobile Crashes at Industrial Scale
arXiv cs.AI Research & Papers
Enhancing Protein Representation Learning via Manifold Restore Mixing
arXiv cs.AI Research & Papers
Distributed Quantum Learning over Near-term Devices: Convergence Analysis and Security De…
arXiv cs.AI Research & Papers
CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded…
arXiv cs.AI Research & Papers
Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents
arXiv cs.AI Research & Papers
Field-level weak lensing cosmology with $<100$ simulations using multifidelity simulation…
arXiv cs.AI Research & Papers
Understanding Privacy by Formalizing It
arXiv cs.AI Research & Papers
A Matter of Time: Towards a General Theory of Agency
arXiv cs.AI Research & Papers
Efficient Safety Benchmarking via Item Response Theory
arXiv cs.AI Research & Papers
Design Principles for Human-Agent Interaction
arXiv cs.AI Research & Papers
SPIRAL: Learning to Search and Aggregate
arXiv cs.AI Research & Papers
Platooning Connected, Autonomous, and Human-Driven Vehicles: A Deep Reinforcement Learnin…
arXiv cs.AI Research & Papers
Distributed Model Predictive Control with Adaptive Safety Zones for Multi-Fleet Drone Ope…
arXiv cs.AI Research & Papers
Robust Auto-associative Memory via Convolutional Restricted Hopfield Networks
arXiv cs.AI Research & Papers
EHR-Complex: Benchmarking Medical Agents for Complex Clinical Reasoning
arXiv cs.AI Research & Papers
Genetic Algorithm Based Coordination and Optimization Model for Generation Grid Load Stor…
arXiv cs.AI Research & Papers
A Formal Tool for Verification of Probabilistic Spiking Neural Networks Based on Quotient…
arXiv cs.AI Research & Papers
Specifying AI-SDLC Processes: A Protocol Language for Human-Agent Boundaries
arXiv cs.AI Research & Papers
DEMM-Bench: A Cross-Regime Benchmark for Agent-Runtime Governance-Evidence Sufficiency
arXiv cs.AI Research & Papers
RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Bl…
arXiv cs.AI Research & Papers
Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems
arXiv cs.AI Research & Papers
Jury Duty: Calibration and Orientation Failures in MLLM-as-a-Judge Under Cultural Ambigui…
arXiv cs.AI Research & Papers
SPARC: A Multi-Agent System for Electrical Circuit Question Answering