Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yiren, Shah, Viraj, Suh, Sangho, Siangliulue, Pao, August, Tal, Huang, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911174363185152
author Liu, Yiren
Shah, Viraj
Suh, Sangho
Siangliulue, Pao
August, Tal
Huang, Yun
author_facet Liu, Yiren
Shah, Viraj
Suh, Sangho
Siangliulue, Pao
August, Tal
Huang, Yun
contents Recent advances in multi-agent systems (MAS) enable tools for information search and ideation by assigning personas to agents. However, how users can effectively control, steer, and critically evaluate collaboration among multiple domain-expert agents remains underexplored. We present Perspectra, an interactive MAS that visualizes and structures deliberation among LLM agents via a forum-style interface, supporting @-mention to invite targeted agents, threading for parallel exploration, with a real-time mind map for visualizing arguments and rationales. In a within-subjects study with 18 participants, we compared Perspectra to a group-chat baseline as they developed research proposals. Our findings show that Perspectra significantly increased the frequency and depth of critical-thinking behaviors, elicited more interdisciplinary replies, and led to more frequent proposal revisions than the group chat condition. We discuss implications for designing multi-agent tools that scaffold critical thinking by supporting user control over multi-agent adversarial discourse.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20553
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
Liu, Yiren
Shah, Viraj
Suh, Sangho
Siangliulue, Pao
August, Tal
Huang, Yun
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Recent advances in multi-agent systems (MAS) enable tools for information search and ideation by assigning personas to agents. However, how users can effectively control, steer, and critically evaluate collaboration among multiple domain-expert agents remains underexplored. We present Perspectra, an interactive MAS that visualizes and structures deliberation among LLM agents via a forum-style interface, supporting @-mention to invite targeted agents, threading for parallel exploration, with a real-time mind map for visualizing arguments and rationales. In a within-subjects study with 18 participants, we compared Perspectra to a group-chat baseline as they developed research proposals. Our findings show that Perspectra significantly increased the frequency and depth of critical-thinking behaviors, elicited more interdisciplinary replies, and led to more frequent proposal revisions than the group chat condition. We discuss implications for designing multi-agent tools that scaffold critical thinking by supporting user control over multi-agent adversarial discourse.
title Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2509.20553