Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game

TL;DR

This paper introduces the Multi-Perspective Team Tactic framework for LLMs, enhancing their decision-making, communication, and human-like reasoning in complex scenarios using the language logic game WIU.

Contribution

It proposes a novel MPTT framework that improves LLMs' multi-dimensional thinking and self-perception in decision-making tasks within the WIU game environment.

Findings

MPTT enables LLMs to make rational decisions through strategic concealment and communication.

The framework fosters human-like trust and fairness in LLM decision-making.

Experiments show LLMs can learn and align with human behaviors in interactive scenarios.

Abstract

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.