ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions
It addresses decision-making challenges for users lacking domain knowledge, offering a more controllable and collaborative approach, though it is incremental as it builds on existing multi-agent systems.
The paper tackles the problem of unfamiliar online decision-making by introducing ChoiceMates, a multi-agent conversational system that allows users to orchestrate LLM agents for assistance. Results from a user evaluation (n=12) show it leads to more confident and satisfactory decisions with better understanding than web search, and higher decision quality and confidence than a commercial multi-agent framework.
From deciding on a PhD program to buying a new camera, unfamiliar decisions--decisions without domain knowledge--are frequent and significant. The complexity and uncertainty of such decisions demand unique approaches to information seeking, understanding, and decision-making. Our formative study highlights that users want to start by discovering broad and relevant domain information evenly and simultaneously, quickly address emerging inquiries, and gain personalized standards to assess information found. We present ChoiceMates, an interactive multi-agent system designed to address these needs by enabling users to engage with a dynamic set of LLM agents each presenting a unique experience in the domain. Unlike existing multi-agent systems that automate tasks with agents, the user orchestrates agents to assist their decision-making process. Our user evaluation (n=12) shows that ChoiceMates enables a more confident, satisfactory decision-making with better situation understanding than web search, and higher decision quality and confidence than a commercial multi-agent framework. This work provides insights into designing a more controllable and collaborative multi-agent system.