Español

Explorar

Noticias de IA

29675 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
MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation
arXiv cs.AI Research & Papers
Beyond Component Testing: Validating Agentic AI Systems
arXiv cs.AI Research & Papers
Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations
arXiv cs.AI Research & Papers
A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-…
arXiv cs.AI Research & Papers
Adaptive Policy Backbone via Shared Network
arXiv cs.AI Research & Papers
ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizo…
arXiv cs.AI Research & Papers
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
arXiv cs.AI Research & Papers
NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observa…
arXiv cs.AI Research & Papers
LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents
arXiv cs.AI Research & Papers
On a joint simultaneous learning of relevant feature subsets and subspaces in regression-…
arXiv cs.AI Research & Papers
HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators
arXiv cs.AI Research & Papers
ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in S…
arXiv cs.AI Research & Papers
CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents
arXiv cs.AI Research & Papers
Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
arXiv cs.AI Research & Papers
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Sca…
arXiv cs.AI Research & Papers
AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair
arXiv cs.AI Research & Papers
QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language …
arXiv cs.AI Research & Papers
Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Mu…
arXiv cs.AI Research & Papers
DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture S…
arXiv cs.AI Research & Papers
Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks
arXiv cs.AI Research & Papers
Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Gener…
arXiv cs.AI Research & Papers
Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search
arXiv cs.AI Research & Papers
Cognitive World Model for Progressive BDI/E Trajectory Evaluation of Conversational Agents
arXiv cs.AI Research & Papers
The persuasive power of large language models does not depend on their perceived national…
arXiv cs.AI Research & Papers
Multi-Granularity Position Embedding of Graphs via Granular-Ball for Link Prediction
arXiv cs.AI Research & Papers
SERUM: State Extraction and Refinement for User Modeling
arXiv cs.AI Research & Papers
Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous T…
arXiv cs.AI Research & Papers
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
arXiv cs.AI Research & Papers
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
arXiv cs.AI Research & Papers
What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents