Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game
This work addresses the problem of improving LLMs' decision-making and social simulation for applications in societal fairness and diversity, though it appears incremental as it builds on existing game-based frameworks.
The paper tackled the challenge of LLMs in open decision-making within complex scenarios by proposing the Multi-Perspective Team Tactic (MPTT) framework using the game 'Who is Undercover?' to enhance human-like language logic and strategic communication, with preliminary results showing it simulates real society and aids minority groups in promoting fairness and diversity.
Large Language Models (LLMs) are pivotal AI agents in complex tasks but still face challenges in open decision-making problems within complex scenarios. To address this, we use the language logic game ``Who is Undercover?'' (WIU) as an experimental platform to propose the Multi-Perspective Team Tactic (MPTT) framework. MPTT aims to cultivate LLMs' human-like language expression logic, multi-dimensional thinking, and self-perception in complex scenarios. By alternating speaking and voting sessions, integrating techniques like self-perspective, identity-determination, self-reflection, self-summary and multi-round find-teammates, LLM agents make rational decisions through strategic concealment and communication, fostering human-like trust. Preliminary results show that MPTT, combined with WIU, leverages LLMs' cognitive capabilities to create a decision-making framework that can simulate real society. This framework aids minority groups in communication and expression, promoting fairness and diversity in decision-making. Additionally, our Human-in-the-loop experiments demonstrate that LLMs can learn and align with human behaviors through interactive, indicating their potential for active participation in societal decision-making.