3 papers
cs.AI2025
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
Shiyi Cao, Dacheng Li, Fangzhou Zhao +12
We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integr…
cs.AI2025
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Dacheng Li, Shiyi Cao, Tyler Griggs +9
Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) that incorporate reflection, backtracking, and self-validation. Howev…
cs.LG2024
Accelerating Direct Preference Optimization with Prefix Sharing
Franklin Wang, Sumanth Hegde
Offline paired preference optimization algorithms have become a popular approach for fine-tuning on preference data, outperforming traditional supervised fine-tuning in various tas…