Español

Explorar

Noticias de IA

37834 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
Cautious Context Steering for Language Model Personalization
arXiv cs.AI Research & Papers
The Ignition Index: Measuring Global Workspace Dynamics in Language Models
arXiv cs.AI Research & Papers
LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs
arXiv cs.AI Research & Papers
TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Tr…
arXiv cs.AI Research & Papers
Recursive Synthesis for Long-Horizon Terminal Tasks
arXiv cs.AI Research & Papers
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
arXiv cs.AI Research & Papers
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing
arXiv cs.AI Research & Papers
C$^3$PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal M…
arXiv cs.AI Research & Papers
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
arXiv cs.AI Research & Papers
Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforceme…
arXiv cs.AI Research & Papers
ECG-LENS: Lead-Aware Clinical Context Enriched ECG Report Generation and Evaluation
arXiv cs.AI Research & Papers
Challenges in Evaluating Explanation Methods for Static and Evolving Data
arXiv cs.AI Research & Papers
Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay
arXiv cs.AI Research & Papers
AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents
arXiv cs.AI Research & Papers
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
arXiv cs.AI Research & Papers
When History Lies: Evaluating and Improving Tool Use under Misleading Multi-Turn Histories
arXiv cs.AI Research & Papers
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
arXiv cs.AI Research & Papers
Skill Neologisms: Towards Skill-based Continual Learning
arXiv cs.AI Research & Papers
Supervised Learning Has a Geometric Blind Spot
arXiv cs.AI Research & Papers
A note on conditional PAC-efficient reasoning in large language model routing
arXiv cs.AI Research & Papers
Trajectory-guided discharge stratification for heart failure using short-context electron…
arXiv cs.AI Research & Papers
Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap
arXiv cs.AI Research & Papers
Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architect…
arXiv cs.AI Research & Papers
Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New S…
arXiv cs.AI Research & Papers
Counterfactual Analysis via Large Language Models
arXiv cs.AI Research & Papers
Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents
arXiv cs.AI Research & Papers
DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinic…
arXiv cs.AI Research & Papers
Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Pla…
arXiv cs.AI Research & Papers
SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language…
arXiv cs.AI Research & Papers
Integrating Implicit and Explicit Relational Biases through Graph-Based Multiple Instance…