ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions

TL;DR

ChoiceMates is a multi-agent conversational system that helps users navigate unfamiliar decisions by enabling interactive, personalized, and collaborative engagement with domain-specific AI agents, improving decision confidence and quality.

Contribution

This work introduces a novel multi-agent system where users orchestrate agents for decision support, enhancing control, collaboration, and decision outcomes in unfamiliar domains.

Findings

Users achieved higher decision confidence than web search.

ChoiceMates improved decision quality over existing frameworks.

Participants reported better understanding and satisfaction.

Abstract

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.