MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations

2025-12-15

AI Summary

To address task failures caused by ambiguous user requests in multi-turn dialogues, this paper proposes the first multi-agent collaborative framework specifically designed for clarification tasks. The framework dynamically determines optimal clarification timing, assigns agent roles (initiator vs. collaborator), and generates role-aware, timing-adaptive interactive clarification queries. It introduces a novel taxonomy of user ambiguity and integrates dialogue state tracking, ambiguity type classification, collaborative strategy modeling, and reinforcement-guided query generation. Experiments on MultiWOZ 2.4 demonstrate significant improvements: task success rate increases by 7.8 percentage points (from 54.5% to 62.3%), and average dialogue turns decrease by 1.67 (from 6.53 to 4.86). These results underscore substantial gains in both robustness of intent understanding under uncertainty and interaction efficiency within multi-agent systems.

Technology Category

• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Multi-Robot Systems

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• Resolves ambiguous user requests in multi-turn conversations
• Determines optimal agent coordination for clarification dialogues
• Increases task success by reducing dialogue turns through proactive clarification

Innovation

• Multi-agent framework for interactive user clarification
• Novel taxonomy categorizing user ambiguities to guide strategies
• Autonomous coordination of agents to interact synergistically with users