Rethinking RL for LLM Reasoning: It’s Sparse Policy Selection, Not Capability Learning
mayo 8, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2605.06241v1 Announce Type: new Abstract: Reinforcement learning has become the standard for improving reasoning in...
Rethinking organizational design in the age of agentic AI
mayo 26, 2026admin NUAI,Committee,Noticias,Uncategorized(0)Amid rapidly growing adoption of enterprise-level AI agents, there’s a disconnect emerging between ambition and...
Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey
febrero 11, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2602.06052v3 Announce Type: replace Abstract: The research of artificial intelligence is undergoing a paradigm shift...
Rethinking AI: DeepSeek’s playbook shakes up the high-spend, high-compute paradigm
junio 15, 2025admin NUAI,Committee,Noticias,Uncategorized(0)DeepSeek’s advancements were inevitable, but the company brought them forward a few years earlier than...
Retail Resurrection: David’s Bridal bets its future on AI after double bankruptcy
junio 28, 2025admin NUAI,Committee,Noticias,Uncategorized(0)How AI-driven personalization, knowledge graphs and a two-sided marketplace are creating a new business model...
Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
febrero 3, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2602.01698v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have recently achieved strong mathematical and...
REST: A Stress-Testing Framework for Evaluating Multi-Problem Reasoning in Large Reasoning Models
julio 27, 2025admin NUAI,Committee,Noticias,Uncategorized(0)Large Reasoning Models (LRMs) have rapidly advanced, exhibiting impressive performance in complex problem-solving tasks across...
Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective
junio 4, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2506.02553v1 Announce Type: cross Abstract: We study a common challenge in reinforcement learning for large...
Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
diciembre 11, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2512.08960v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers...
