用规则引擎+LLM打造更像真人的人狼游戏智能体
An Implementation of Werewolf Agent That does not Truly Trust LLMs
- 用规则判断何时用LLM输出或预设模板
- 能反驳、识破谎言并保持角色一致性
- 比纯LLM更像真人，适合人狼游戏研究
人狼游戏是不完全信息博弈，计算机玩家面临情境理解不足和表达缺乏个性的挑战（如无法进行角色化发言或情境性说谎）。本文提出一种结合大型语言模型（LLM）与规则算法的人狼游戏智能体。该智能体通过分析对话历史，由规则系统决定输出来源：要么来自LLM生成内容，要么来自预先准备的模板。该机制使智能体能在特定情况下反驳、识别对话结束时机，并保持角色人格特征。实验表明，该方法有效缓解了对话不一致问题，实现了更符合逻辑的发言。定性评估显示，相比未修改的LLM，本智能体被感知为更具人类特征。代码已开源，以推动人狼游戏相关研究。
原文摘要 · Abstract (English)
Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player given the lack of understanding of the situation and individuality of utterance (e.g., computer agents are not capable of characterful utterance or situational lying). We propose a werewolf agent that solves some of those difficulties by combining a Large Language Model (LLM) and a rule-based algorithm. In particular, our agent uses a rule-based algorithm to select an output either from an LLM or a template prepared beforehand based on the results of analyzing conversation history using an LLM. It allows the agent to refute in specific situations, identify when to end the conversation, and behave with persona. This approach mitigated conversational inconsistencies and facilitated logical utterance as a result. We also conducted a qualitative evaluation, which resulted in our agent being perceived as more human-like compared to an unmodified LLM. The agent is freely available for contributing to advance the research in the field of Werewolf game.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。