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
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
arXiv cs.AI Research & Papers
Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents
arXiv cs.AI Research & Papers
The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable C…
arXiv cs.AI Research & Papers
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Conte…
arXiv cs.AI Research & Papers
FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
arXiv cs.AI Research & Papers
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Ca…
arXiv cs.AI Research & Papers
Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy F…
arXiv cs.AI Research & Papers
A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimater…
arXiv cs.AI Research & Papers
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
arXiv cs.AI Research & Papers
Finding H. pylori in the Fine Print: Evidence-Linked Multi-Agent Case Finding from Gastri…
arXiv cs.AI Research & Papers
A Definition and Roadmap for World Models
arXiv cs.AI Research & Papers
TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Fo…
arXiv cs.AI Research & Papers
Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models
arXiv cs.AI Research & Papers
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
arXiv cs.AI Research & Papers
From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an E…
arXiv cs.AI Research & Papers
Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale
arXiv cs.AI Research & Papers
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout A…
arXiv cs.AI Research & Papers
A toy framework for single and multi-agent human-AI curiosity ecosystems
arXiv cs.AI Research & Papers
AgoraSim: A Hybrid Agent-Based Modeling Framework
arXiv cs.AI Research & Papers
Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation
arXiv cs.AI Research & Papers
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulat…
arXiv cs.AI Research & Papers
PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation
arXiv cs.AI Research & Papers
Uncovering Latent Depression Severity for Binary Depression Detection via Advantage-weigh…
arXiv cs.AI Research & Papers
StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems
arXiv cs.AI Research & Papers
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Traini…
arXiv cs.AI Research & Papers
From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structure…
arXiv cs.AI Research & Papers
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Larg…
arXiv cs.AI Research & Papers
Synthetic Consumer Insight Generation with Large Language Models
arXiv cs.AI Research & Papers
ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation
arXiv cs.AI Research & Papers
Memory in the Loop: In-Process Retrieval as ExtendedWorking Memory for Language Agents