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
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
arXiv cs.AI Research & Papers
S3TS: Stochastic Scenario-Structured Tree Search for Advanced Planning Under Uncertainty
arXiv cs.AI Research & Papers
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectori…
arXiv cs.AI Research & Papers
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Pe…
arXiv cs.AI Research & Papers
Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs …
arXiv cs.AI Research & Papers
Beyond Access: Guided LLM Scaffolding for Independent Learning in Undergraduate Statistics
arXiv cs.AI Research & Papers
Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners
arXiv cs.AI Research & Papers
Structure-Guided Adaptive Propagation for Protein-Protein Interaction Site Prediction
arXiv cs.AI Research & Papers
TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination
arXiv cs.AI Research & Papers
Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simu…
arXiv cs.AI Research & Papers
Joint Agent Memory and Exploration Learning via Novelty Signals
arXiv cs.AI Research & Papers
Transferring Information Across Interventions in Causal Bayesian Optimization
arXiv cs.AI Research & Papers
Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observ…
arXiv cs.AI Research & Papers
Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems
arXiv cs.AI Research & Papers
ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
arXiv cs.AI Research & Papers
Application of Algorithms in Energy-Efficient Design Platforms for Green Building
arXiv cs.AI Research & Papers
Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification
arXiv cs.AI Research & Papers
Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-…
arXiv cs.AI Research & Papers
TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Plan…
arXiv cs.AI Research & Papers
Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach
arXiv cs.AI Research & Papers
Relational Intervention During Functional Collapse in Large Language Models: A Lexical-St…
arXiv cs.AI Research & Papers
Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
arXiv cs.AI Research & Papers
TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages
arXiv cs.AI Research & Papers
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cog…
arXiv cs.AI Research & Papers
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
arXiv cs.AI Research & Papers
TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
arXiv cs.AI Research & Papers
Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
arXiv cs.AI Research & Papers
VESTA: Visual Exploration with Statistical Tool Agents
arXiv cs.AI Research & Papers
Evaluating Bivariate Causal Statements Based on Mutual Compatibility
arXiv cs.AI Research & Papers
Capability Self-Assessment: Teaching LLMs to Know Their Limits