MAP: Multi-user Personalization with Collaborative LLM-powered Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Christine, Choi, Jihye, Mutlu, Bilge
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908274077466624
author Lee, Christine
Choi, Jihye
Mutlu, Bilge
author_facet Lee, Christine
Choi, Jihye
Mutlu, Bilge
contents The widespread adoption of Large Language Models (LLMs) and LLM-powered agents in multi-user settings underscores the need for reliable, usable methods to accommodate diverse preferences and resolve conflicting directives. Drawing on conflict resolution theory, we introduce a user-centered workflow for multi-user personalization comprising three stages: Reflection, Analysis, and Feedback. We then present MAP -- a \textbf{M}ulti-\textbf{A}gent system for multi-user \textbf{P}ersonalization -- to operationalize this workflow. By delegating subtasks to specialized agents, MAP (1) retrieves and reflects on relevant user information, while enhancing reliability through agent-to-agent interactions, (2) provides detailed analysis for improved transparency and usability, and (3) integrates user feedback to iteratively refine results. Our user study findings (n=12) highlight MAP's effectiveness and usability for conflict resolution while emphasizing the importance of user involvement in resolution verification and failure management. This work highlights the potential of multi-agent systems to implement user-centered, multi-user personalization workflows and concludes by offering insights for personalization in multi-user contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12757
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAP: Multi-user Personalization with Collaborative LLM-powered Agents
Lee, Christine
Choi, Jihye
Mutlu, Bilge
Human-Computer Interaction
Artificial Intelligence
Robotics
I.2.7; I.2.9; I.2.1
The widespread adoption of Large Language Models (LLMs) and LLM-powered agents in multi-user settings underscores the need for reliable, usable methods to accommodate diverse preferences and resolve conflicting directives. Drawing on conflict resolution theory, we introduce a user-centered workflow for multi-user personalization comprising three stages: Reflection, Analysis, and Feedback. We then present MAP -- a \textbf{M}ulti-\textbf{A}gent system for multi-user \textbf{P}ersonalization -- to operationalize this workflow. By delegating subtasks to specialized agents, MAP (1) retrieves and reflects on relevant user information, while enhancing reliability through agent-to-agent interactions, (2) provides detailed analysis for improved transparency and usability, and (3) integrates user feedback to iteratively refine results. Our user study findings (n=12) highlight MAP's effectiveness and usability for conflict resolution while emphasizing the importance of user involvement in resolution verification and failure management. This work highlights the potential of multi-agent systems to implement user-centered, multi-user personalization workflows and concludes by offering insights for personalization in multi-user contexts.
title MAP: Multi-user Personalization with Collaborative LLM-powered Agents
topic Human-Computer Interaction
Artificial Intelligence
Robotics
I.2.7; I.2.9; I.2.1
url https://arxiv.org/abs/2503.12757