2024/08/20 by Jonathan Light, Light, Jonathan, Cai Min +13 · 7 citations
Business, Management and Accounting · Computer Science · #Artificial Intelligence (cs.AI) #Big Data and Business Intelligence #Computation and Language (cs.CL) #Data Mining Algorithms and Applications #Educational Technology and Assessment #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2408.10635
openalex publication_date 2024/08/20 · openalex created_date 2024/10/01 · openalex updated_date 2026/07/28
Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but struggle with tasks that require detailed planning and decision-making in complex action spaces. We introduce STRATEGIST, a novel approach that integrates the strengths of both methods. Our approach leverages LLMs to search and update high-level strategies (as text), which are then refined and executed by low-level Monte Carlo Tree Search (MCTS). STRATEGIST is a generalizable framework to optimize the strategy through population-based self-play simulations without the need for any training data. We demonstrate the effectiveness of STRATEGIST in learning optimal strategies for competitive, multi-turn games with partial information, including Game of Pure Strategy (GOPS) and multi-agent, hidden-identity discussion games like The Resistance: Avalon. Our results show that agents equipped with STRATEGIST outperform those trained with traditional RL methods, other LLM-based skill acquisition techniques, pre-existing LLM agents across both game environments and achieves comparable performance against human players.