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
ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents
arXiv cs.AI Research & Papers
A Novel Data Augmentation Strategy for Robust Deep Learning Classification of Biomedical …
arXiv cs.AI Research & Papers
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment …
arXiv cs.AI Research & Papers
Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resourc…
arXiv cs.AI Research & Papers
Consistency Training while Mitigating Obfuscation via Rate Matching
arXiv cs.AI Research & Papers
Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018…
arXiv cs.AI Research & Papers
Unsupervised Cognition
arXiv cs.AI Research & Papers
FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-O…
arXiv cs.AI Research & Papers
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Diverge…
arXiv cs.AI Research & Papers
HLL: Can Agents Cross Humanity's Last Line of Verification?
arXiv cs.AI Research & Papers
LLM-Evolved Pattern Generators for Optimal Classical Planning
arXiv cs.AI Research & Papers
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Po…
arXiv cs.AI Research & Papers
A Mathematical Conflict Framework for Contextual Data Modulation
arXiv cs.AI Research & Papers
Learning When to Translate for Multilingual Reasoning
arXiv cs.AI Research & Papers
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
arXiv cs.AI Research & Papers
Monitoring Agentic Systems Before They're Reliable
arXiv cs.AI Research & Papers
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
arXiv cs.AI Research & Papers
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Train…
arXiv cs.AI Research & Papers
Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Es…
arXiv cs.AI Research & Papers
Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filter…
arXiv cs.AI Research & Papers
One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Rewa…
arXiv cs.AI Research & Papers
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbat…
arXiv cs.AI Research & Papers
Learning to Reduce Search Space for Generalizable Neural Routing Solver
arXiv cs.AI Research & Papers
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Miti…
arXiv cs.AI Research & Papers
Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Ke…
arXiv cs.AI Research & Papers
Coordination Graphs for Constrained Multi-Agent Reinforcement Learning
arXiv cs.AI Research & Papers
Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions
arXiv cs.AI Research & Papers
ACON: Optimizing Context Compression for Long-horizon LLM Agents
arXiv cs.AI Research & Papers
A Unified Evaluation-Instructed Framework for Query-Dependent Prompt Optimization
arXiv cs.AI Research & Papers
Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning