References & Citations
Computer Science > Artificial Intelligence
Title: Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games
(Submitted on 1 Dec 2023 (v1), last revised 29 Feb 2024 (this version, v2))
Abstract: In this study, we explore the application of Large Language Models (LLMs) in \textit{Jubensha}, a Chinese detective role-playing game and a novel area in Artificial Intelligence (AI) driven gaming. We introduce the first dataset specifically for Jubensha, including character scripts and game rules, to foster AI agent development in this complex narrative environment. Our work also presents a unique multi-agent interaction framework using LLMs, allowing AI agents to autonomously engage in this game. To evaluate the gaming performance of these AI agents, we developed novel methods measuring their mastery of case information and reasoning skills. Furthermore, we incorporated the latest advancements in in-context learning to improve the agents' performance in information gathering, murderer identification, and logical reasoning. The experimental results validate the effectiveness of our proposed methods. This work aims to offer a novel perspective on understanding LLM capabilities and establish a new benchmark for evaluating large language model-based agents.
Submission history
From: Haochen Shi [view email][v1] Fri, 1 Dec 2023 17:33:57 GMT (9017kb,D)
[v2] Thu, 29 Feb 2024 06:24:28 GMT (25522kb,D)
Link back to: arXiv, form interface, contact.