![[2310.01331] ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2310.01331] ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions
Summary
The paper presents ChoiceMates, a multi-agent system designed to assist users in making unfamiliar online decisions by facilitating interactions with various LLM agents, enhancing decision quality and confidence.
Why It Matters
As online decision-making becomes increasingly complex, tools like ChoiceMates are crucial for helping users navigate unfamiliar domains. This research addresses the need for personalized, interactive decision support systems that improve user confidence and satisfaction.
Key Takeaways
- ChoiceMates allows users to interact with multiple LLM agents for better decision-making.
- The system improves user confidence and satisfaction compared to traditional web searches.
- Personalized standards for assessing information enhance the decision-making process.
- User evaluations indicate higher decision quality than existing commercial frameworks.
- The study provides insights into designing more controllable multi-agent systems.
Computer Science > Human-Computer Interaction arXiv:2310.01331 (cs) [Submitted on 2 Oct 2023 (v1), last revised 19 Feb 2026 (this version, v4)] Title:ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions Authors:Jeongeon Park, Bryan Min, Kihoon Son, Jean Y. Song, Xiaojuan Ma, Juho Kim View a PDF of the paper titled ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions, by Jeongeon Park and 5 other authors View PDF HTML (experimental) 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-mak...
