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
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emerge…
arXiv cs.AI Research & Papers
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
arXiv cs.AI Research & Papers
Automated grading of Linux/bash examinations using large language models: a four-level co…
arXiv cs.AI Research & Papers
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
arXiv cs.AI Research & Papers
Steerability via constraints: a substrate for scalable oversight of coding agents
arXiv cs.AI Research & Papers
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
arXiv cs.AI Research & Papers
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in …
arXiv cs.AI Research & Papers
A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
arXiv cs.AI Research & Papers
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
arXiv cs.AI Research & Papers
Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support
arXiv cs.AI Research & Papers
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
arXiv cs.AI Research & Papers
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
arXiv cs.AI Research & Papers
Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training
arXiv cs.AI Research & Papers
ContextNest: Verifiable Context Governance for Autonomous AI Agent
arXiv cs.AI Research & Papers
SUNTA: Hierarchical Video Prediction with Surprise-based Chunking
arXiv cs.AI Research & Papers
Evidence-State Rewards for Long-Context Reasoning
arXiv cs.AI Research & Papers
Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding …
arXiv cs.AI Research & Papers
Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block …
arXiv cs.AI Research & Papers
CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection
arXiv cs.AI Research & Papers
Safety Targeted Embedding Exploit via Refinement
arXiv cs.AI Research & Papers
CLAP: Closed-Loop Training, Evaluation, and Release Control for Domain Agent Post-training
arXiv cs.AI Research & Papers
Actual causality in fault trees
arXiv cs.AI Research & Papers
Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Know…
arXiv cs.AI Research & Papers
MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision …
arXiv cs.AI Research & Papers
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
arXiv cs.AI Research & Papers
Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis
arXiv cs.AI Research & Papers
Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts
arXiv cs.AI Research & Papers
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
arXiv cs.AI Research & Papers
Meta-Benchmarks for Financial-Services LLM Evaluation
arXiv cs.AI Research & Papers
Reformalization of the Jordan Curve Theorem