Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search

Jonathan Light, Min Cai, WEIQIN CHEN, Guanzhi Wang, Xiusi Chen, Wei Cheng, Yisong Yue, Ziniu Hu

Keywords: self-play, games, LLMs, self-improve, skill-learning

TL;DR: We propose a new method to acquire new skills through bi-level search and demonstrate its performance in multi-agent game settings

Abstract: In this paper, we propose a new method Strategist that utilizes LLMs to acquire new skills for playing multi-agent games through a self-improvement process. Our method gathers quality feedback through self-play simulations with Monte Carlo tree search and LLM-based reflection, which can then be used to learn high-level strategic skills such as how to evaluate states that guide the low-level execution. We showcase how our method can be used in both action planning and dialogue generation in the context of games, achieving good performance on both tasks. Specifically, we demonstrate that our method can help train agents with better performance than both traditional reinforcement learning-based approaches and other LLM-based skill learning approaches in the games of Game of Pure Strategy (GOPS) and Resistance: Avalon.

Submission Number: 26