Saved in:
Bibliographic Details
Main Authors: Acikgoz, Emre Can, Oh, Jinoh, Jeon, Joo Hyuk, Hao, Jie, Ji, Heng, Hakkani-Tür, Dilek, Tur, Gokhan, Li, Xiang, Ma, Chengyuan, Fan, Xing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.13154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909962981081088
author Acikgoz, Emre Can
Oh, Jinoh
Jeon, Joo Hyuk
Hao, Jie
Ji, Heng
Hakkani-Tür, Dilek
Tur, Gokhan
Li, Xiang
Ma, Chengyuan
Fan, Xing
author_facet Acikgoz, Emre Can
Oh, Jinoh
Jeon, Joo Hyuk
Hao, Jie
Ji, Heng
Hakkani-Tür, Dilek
Tur, Gokhan
Li, Xiang
Ma, Chengyuan
Fan, Xing
contents Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applications favor multi-agent architectures to manage complex conversational scenarios efficiently, ambiguity resolution remains a critical and underexplored challenge--particularly due to the difficulty of determining which agent should initiate a clarification and how agents should coordinate their actions when faced with uncertain or incomplete user input. The fundamental questions of when to interrupt a user and how to formulate the optimal clarification query within the most optimal multi-agent settings remain open. In this paper, we propose MAC (Multi-Agent Clarification), an interactive multi-agent framework specifically optimized to resolve user ambiguities by strategically managing clarification dialogues. We first introduce a novel taxonomy categorizing user ambiguities to systematically guide clarification strategies. Then, we present MAC that autonomously coordinates multiple agents to interact synergistically with users. Empirical evaluations on MultiWOZ 2.4 demonstrate that enabling clarification at both levels increases task success rate 7.8\% (54.5 to 62.3) and reduces the average number of dialogue turns (6.53 to 4.86) by eliciting all required user information up front and minimizing repetition. Our findings highlight the importance of active user interaction and role-aware clarification for more reliable human-agent communication.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
Acikgoz, Emre Can
Oh, Jinoh
Jeon, Joo Hyuk
Hao, Jie
Ji, Heng
Hakkani-Tür, Dilek
Tur, Gokhan
Li, Xiang
Ma, Chengyuan
Fan, Xing
Artificial Intelligence
Computation and Language
Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applications favor multi-agent architectures to manage complex conversational scenarios efficiently, ambiguity resolution remains a critical and underexplored challenge--particularly due to the difficulty of determining which agent should initiate a clarification and how agents should coordinate their actions when faced with uncertain or incomplete user input. The fundamental questions of when to interrupt a user and how to formulate the optimal clarification query within the most optimal multi-agent settings remain open. In this paper, we propose MAC (Multi-Agent Clarification), an interactive multi-agent framework specifically optimized to resolve user ambiguities by strategically managing clarification dialogues. We first introduce a novel taxonomy categorizing user ambiguities to systematically guide clarification strategies. Then, we present MAC that autonomously coordinates multiple agents to interact synergistically with users. Empirical evaluations on MultiWOZ 2.4 demonstrate that enabling clarification at both levels increases task success rate 7.8\% (54.5 to 62.3) and reduces the average number of dialogue turns (6.53 to 4.86) by eliciting all required user information up front and minimizing repetition. Our findings highlight the importance of active user interaction and role-aware clarification for more reliable human-agent communication.
title MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2512.13154