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
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
arXiv cs.AI Research & Papers
Generalist AI Control: Towards Multi-purpose Adaptive Algorithms
arXiv cs.AI Research & Papers
Berkeley and Heiserman as an Unexhausted Architecture for Embodied Machine Intelligence
arXiv cs.AI Research & Papers
LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Mode…
arXiv cs.AI Research & Papers
Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection
arXiv cs.AI Research & Papers
DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidan…
arXiv cs.AI Research & Papers
RECON: Benchmarking Agent Memory for Compositional Reasoning over Long Contexts
arXiv cs.AI Research & Papers
Constraint-Anchored Reasoning Traces
arXiv cs.AI Research & Papers
RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Pl…
arXiv cs.AI Research & Papers
From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data
arXiv cs.AI Research & Papers
Environment-free Synthetic Data Generation for API-Calling Agents
arXiv cs.AI Research & Papers
Lomekwi: Resource-Bounded Tool Discovery in LLM Agents
arXiv cs.AI Research & Papers
Expected Free Energy as Belief-Dependent Utility for rho-POMDPs
arXiv cs.AI Research & Papers
PriorProof: A Point-in-Time Measure of Technique Novelty for Formal Proofs
arXiv cs.AI Research & Papers
Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Aut…
arXiv cs.AI Research & Papers
When LLMs Over-Answer: Measuring and Mitigating Quality Issues in LLM-Based Hardware Desc…
arXiv cs.AI Research & Papers
Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-…
arXiv cs.AI Research & Papers
Fourier Geometric Wind Power Forecasting with Numerical Weather Prediction
arXiv cs.AI Research & Papers
A Diagnostic Framework for AI Agent Behavior
arXiv cs.AI Research & Papers
Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase…
arXiv cs.AI Research & Papers
Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, …
arXiv cs.AI Research & Papers
Constrained Path Reasoning: Measuring When Committed Stages Earn Their Cost
arXiv cs.AI Research & Papers
LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinfo…
arXiv cs.AI Research & Papers
Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations
arXiv cs.AI Research & Papers
An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation…
arXiv cs.AI Research & Papers
Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware
arXiv cs.AI Research & Papers
Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift
arXiv cs.AI Research & Papers
Intermittent Control Is Not Diluted Control: A Switching Effect in Artificial Agency
arXiv cs.AI Research & Papers
Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During D…
arXiv cs.AI Research & Papers
Panache: One-Pass Motif Discovery at Every Window Length