Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games

IntroductionMulti-agent systems utilizing large language models (LLMs) have shown great promise in achieving natural dialogue. However, smooth dialogue control and autonomous decision making among agents still remain challenging.MethodsIn this study, we focus on conversational norms such as adjacenc...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryota Nonomura, Hiroki Mori
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1582287/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849421831883194368
author Ryota Nonomura
Hiroki Mori
author_facet Ryota Nonomura
Hiroki Mori
author_sort Ryota Nonomura
collection DOAJ
description IntroductionMulti-agent systems utilizing large language models (LLMs) have shown great promise in achieving natural dialogue. However, smooth dialogue control and autonomous decision making among agents still remain challenging.MethodsIn this study, we focus on conversational norms such as adjacency pairs and turn-taking found in conversation analysis and propose a new framework called “Murder Mystery Agents” that applies these norms to AI agents' dialogue control. As an evaluation target, we employed the “Murder Mystery” game, a reasoning-type table-top role-playing game that requires complex social reasoning and information manipulation. The proposed framework integrates next speaker selection based on adjacency pairs and a self-selection mechanism that takes agents' internal states into account to achieve more natural and strategic dialogue.ResultsTo verify the effectiveness of this new approach, we analyzed utterances that led to dialogue breakdowns and conducted automatic evaluation using LLMs, as well as human evaluation using evaluation criteria developed for the Murder Mystery game. Experimental results showed that the implementation of the next speaker selection mechanism significantly reduced dialogue breakdowns and improved the ability of agents to share information and perform logical reasoning.DiscussionThe results of this study demonstrate that the systematics of turn-taking in human conversation are also effective in controlling dialogue among AI agents, and provide design guidelines for more advanced multi-agent dialogue systems.
format Article
id doaj-art-ae63fa62143249cc8677a3b66e85759d
institution Kabale University
issn 2624-8212
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-ae63fa62143249cc8677a3b66e85759d2025-08-20T03:31:21ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-06-01810.3389/frai.2025.15822871582287Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery gamesRyota NonomuraHiroki MoriIntroductionMulti-agent systems utilizing large language models (LLMs) have shown great promise in achieving natural dialogue. However, smooth dialogue control and autonomous decision making among agents still remain challenging.MethodsIn this study, we focus on conversational norms such as adjacency pairs and turn-taking found in conversation analysis and propose a new framework called “Murder Mystery Agents” that applies these norms to AI agents' dialogue control. As an evaluation target, we employed the “Murder Mystery” game, a reasoning-type table-top role-playing game that requires complex social reasoning and information manipulation. The proposed framework integrates next speaker selection based on adjacency pairs and a self-selection mechanism that takes agents' internal states into account to achieve more natural and strategic dialogue.ResultsTo verify the effectiveness of this new approach, we analyzed utterances that led to dialogue breakdowns and conducted automatic evaluation using LLMs, as well as human evaluation using evaluation criteria developed for the Murder Mystery game. Experimental results showed that the implementation of the next speaker selection mechanism significantly reduced dialogue breakdowns and improved the ability of agents to share information and perform logical reasoning.DiscussionThe results of this study demonstrate that the systematics of turn-taking in human conversation are also effective in controlling dialogue among AI agents, and provide design guidelines for more advanced multi-agent dialogue systems.https://www.frontiersin.org/articles/10.3389/frai.2025.1582287/fullturn-takingconversation analysisgenerative AILLM-based agentmulti-party conversation
spellingShingle Ryota Nonomura
Hiroki Mori
Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games
Frontiers in Artificial Intelligence
turn-taking
conversation analysis
generative AI
LLM-based agent
multi-party conversation
title Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games
title_full Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games
title_fullStr Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games
title_full_unstemmed Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games
title_short Who speaks next? Multi-party AI discussion leveraging the systematics of turn-taking in Murder Mystery games
title_sort who speaks next multi party ai discussion leveraging the systematics of turn taking in murder mystery games
topic turn-taking
conversation analysis
generative AI
LLM-based agent
multi-party conversation
url https://www.frontiersin.org/articles/10.3389/frai.2025.1582287/full
work_keys_str_mv AT ryotanonomura whospeaksnextmultipartyaidiscussionleveragingthesystematicsofturntakinginmurdermysterygames
AT hirokimori whospeaksnextmultipartyaidiscussionleveragingthesystematicsofturntakinginmurdermysterygames