Enhance Reasoning for Large Language Models in the Game Werewolf

arXiv:2402.02330v2 Announce Type: replace-cross
Abstract: This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents. Unlike augmenting LLMs with prompt engineering, Thinker directly harnesses knowledge from databases and employs various optimization techniques. The framework forms a reasoning hierarchy where LLMs handle intuitive System-1 tasks such as natural language processing, while the Thinker focuses on cognitive System-2 tasks that require complex logical analysis and domain-specific knowledge. …

abstract agents arxiv capabilities cs.ai cs.cl databases engineering forms framework game knowledge language language models large language large language models llm llms optimization paper prompt reasoning type