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
Learning Urban Access Costs from Origin-Destination Flows via Inverse Optimal Transport
arXiv cs.AI Research & Papers
MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic De…
arXiv cs.AI Research & Papers
GAGPO: Generalized Advantage Grouped Policy Optimization
arXiv cs.AI Research & Papers
Abstracting Cross-Domain Action Sequences into Interpretable Workflows
arXiv cs.AI Research & Papers
Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-L…
arXiv cs.AI Research & Papers
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
arXiv cs.AI Research & Papers
StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
arXiv cs.AI Research & Papers
When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Strong…
arXiv cs.AI Research & Papers
GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Me…
arXiv cs.AI Research & Papers
Causal Object-Centric Models for Planning with Monte Carlo Tree Search
arXiv cs.AI Research & Papers
CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning
arXiv cs.AI Research & Papers
Communication Policy Evolution for Proactive LLM Agents
arXiv cs.AI Research & Papers
AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties
arXiv cs.AI Research & Papers
SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing
arXiv cs.AI Research & Papers
Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
arXiv cs.AI Research & Papers
When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Re…
arXiv cs.AI Research & Papers
VeriGeo: Controllable Geometry Question Generation with Numerical and Analytical Verifica…
arXiv cs.AI Research & Papers
FactoryLLM: A Safe and Open-Source AI Playground for Evaluating LLMs in Smart Factories
arXiv cs.AI Research & Papers
Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Accepta…
arXiv cs.AI Research & Papers
Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formaliza…
arXiv cs.AI Research & Papers
A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Do…
arXiv cs.AI Research & Papers
Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privile…
arXiv cs.AI Research & Papers
When and How Severely: Scenario-Specific Safety Envelopes for Driving VLAs
arXiv cs.AI Research & Papers
MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analys…
arXiv cs.AI Research & Papers
AI Receptivity or AI Adoption Breadth? A Tool-Specific Reanalysis of the Lower-Literacy/H…
arXiv cs.AI Research & Papers
When Sample Selection Bias Precipitates Model Collapse
arXiv cs.AI Research & Papers
Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP
arXiv cs.AI Research & Papers
WorkBench Revisited: Workplace Agents Two Years On
arXiv cs.AI Research & Papers
Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher
arXiv cs.AI Research & Papers
Orchestra-o1: Omnimodal Agent Orchestration