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
CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
arXiv cs.AI Research & Papers
Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors …
arXiv cs.AI Research & Papers
Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Un…
arXiv cs.AI Research & Papers
Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
arXiv cs.AI Research & Papers
Evaluating Research-Level Math Proofs via Strict Step-Level Verification
arXiv cs.AI Research & Papers
READER: Robust Evidence-based Authorship Decoding via Extracted Representations
arXiv cs.AI Research & Papers
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
arXiv cs.AI Research & Papers
Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimizati…
arXiv cs.AI Research & Papers
Expert-Level Crisis Detection in Mental Health Conversations
arXiv cs.AI Research & Papers
HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning
arXiv cs.AI Research & Papers
A Reliable Fault Diagnosis Method Based on Belief Rule Base Consider Robustness Analysis
arXiv cs.AI Research & Papers
Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in…
arXiv cs.AI Research & Papers
Mobility Anomaly Generation using LLM-Driven Behavior with Kinematic Constraints
arXiv cs.AI Research & Papers
Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artif…
arXiv cs.AI Research & Papers
Sim2Schedule: A Simulator-Guided LLM Framework for Autonomous Open-Pit Mine Scheduling
arXiv cs.AI Research & Papers
Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction
arXiv cs.AI Research & Papers
RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning
arXiv cs.AI Research & Papers
Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with A…
arXiv cs.AI Research & Papers
Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LL…
arXiv cs.AI Research & Papers
Deployment-Time Memorization in Foundation-Model Agents
arXiv cs.AI Research & Papers
CleanPatrick: A Benchmark for Image Data Cleaning
arXiv cs.AI Research & Papers
Decentralized Multi-Agent Systems with Shared Context
arXiv cs.AI Research & Papers
Post-Quantum Secure Federated DeFi for Inclusive Banking
arXiv cs.AI Research & Papers
Dynamic Linear Attention
arXiv cs.AI Research & Papers
Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Mode…
arXiv cs.AI Research & Papers
Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting
arXiv cs.AI Research & Papers
Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation
arXiv cs.AI Research & Papers
Embedding Hybrid Systems into Continuous Latent Vector Fields
arXiv cs.AI Research & Papers
Towards Diverse Scientific Hypothesis Search with Large Language Models
arXiv cs.AI Research & Papers
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unifie…