Español

Explorar

Noticias de IA

22318 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
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Pe…
arXiv cs.AI Research & Papers
GRASP: GRanularity-Aware Search Policy for Agentic RAG
arXiv cs.AI Research & Papers
Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial …
arXiv cs.AI Research & Papers
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
arXiv cs.AI Research & Papers
Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Re…
arXiv cs.AI Research & Papers
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large L…
arXiv cs.AI Research & Papers
Can Agentic Trading Systems Pay for Their Own Intelligence?
arXiv cs.AI Research & Papers
Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models
arXiv cs.AI Research & Papers
When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Base…
arXiv cs.AI Research & Papers
KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quali…
arXiv cs.AI Research & Papers
GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention
arXiv cs.AI Research & Papers
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
arXiv cs.AI Research & Papers
IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation
arXiv cs.AI Research & Papers
Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
arXiv cs.AI Research & Papers
Looped State-Space Language Models with Adaptive Exit-State Selection
arXiv cs.AI Research & Papers
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
arXiv cs.AI Research & Papers
From ambiguous utterances to governed reuse classes: canonicalization, quotient invarianc…
arXiv cs.AI Research & Papers
AgentAbstain: Do LLM Agents Know When Not to Act?
arXiv cs.AI Research & Papers
A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Exec…
arXiv cs.AI Research & Papers
TopoExplore: Topological Discrimination for Archive-Based Exploration
arXiv cs.AI Research & Papers
Exploring Agentic Workflows for Generating High Quality Math Visual Aids
arXiv cs.AI Research & Papers
Agentic Context Learning with Self-Discovered Specification
arXiv cs.AI Research & Papers
PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input…
arXiv cs.AI Research & Papers
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
arXiv cs.AI Research & Papers
Verification of Adaptive Agentic Controllers through Finite Rule Revision
arXiv cs.AI Research & Papers
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
arXiv cs.AI Research & Papers
BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and B…
arXiv cs.AI Research & Papers
Task-Conditioned Synthetic Data Generation for Improving Machine Learning Performance in …
arXiv cs.AI Research & Papers
A Dynamic Scene Interaction Reasoning Framework for Scene-level Lane-Change Intention and…
arXiv cs.AI Research & Papers
Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Bench…