Learning to Reason in Structured In-context Environments with Reinforcement Learning

​NICE Talk 153🌟 invites Peng Yu, a PhD student at SJTU, to discuss Structured In-context Environments (SIE) for enhancing the model's reasoning environment.

​🙃Traditional mathematical or coding environments rely heavily on expensive expert annotations, while the skills learned in game-like environments are difficult to generalize.

​🧐 An ideal LLM Reasoning training environment must simultaneously possess three core features: Scalability, support for Generalizable Reasoning, and Verifiability.

​☺️The SIE framework proposes to automatically construct an inference environment from massive structured data, such as knowledge graphs.

​paper: https://openreview.net/pdf?id=CicK2lJMUy