PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Qinglin, Zhao, Runcong, Liang, Bin, Du, Jinhua, Gui, Lin, He, Yulan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913847249469440
author Zhu, Qinglin
Zhao, Runcong
Liang, Bin
Du, Jinhua
Gui, Lin
He, Yulan
author_facet Zhu, Qinglin
Zhao, Runcong
Liang, Bin
Du, Jinhua
Gui, Lin
He, Yulan
contents We introduce WellPlay, a reasoning dataset for multi-agent conversational inference in Murder Mystery Games (MMGs). WellPlay comprises 1,482 inferential questions across 12 games, spanning objectives, reasoning, and relationship understanding, and establishes a systematic benchmark for evaluating agent reasoning abilities in complex social settings. Building on this foundation, we present PLAYER*, a novel framework for Large Language Model (LLM)-based agents in MMGs. MMGs pose unique challenges, including undefined state spaces, absent intermediate rewards, and the need for strategic reasoning through natural language. PLAYER* addresses these challenges with a sensor-based state representation and an information-driven strategy that optimises questioning and suspect pruning. Experiments show that PLAYER* outperforms existing methods in reasoning accuracy, efficiency, and agent-human interaction, advancing reasoning agents for complex social scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2404_17662
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
Zhu, Qinglin
Zhao, Runcong
Liang, Bin
Du, Jinhua
Gui, Lin
He, Yulan
Computation and Language
We introduce WellPlay, a reasoning dataset for multi-agent conversational inference in Murder Mystery Games (MMGs). WellPlay comprises 1,482 inferential questions across 12 games, spanning objectives, reasoning, and relationship understanding, and establishes a systematic benchmark for evaluating agent reasoning abilities in complex social settings. Building on this foundation, we present PLAYER*, a novel framework for Large Language Model (LLM)-based agents in MMGs. MMGs pose unique challenges, including undefined state spaces, absent intermediate rewards, and the need for strategic reasoning through natural language. PLAYER* addresses these challenges with a sensor-based state representation and an information-driven strategy that optimises questioning and suspect pruning. Experiments show that PLAYER* outperforms existing methods in reasoning accuracy, efficiency, and agent-human interaction, advancing reasoning agents for complex social scenarios.
title PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
topic Computation and Language
url https://arxiv.org/abs/2404.17662