Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
This addresses the challenge for researchers and users of multi-agent tools in enhancing critical thinking and control over adversarial discourse, representing an incremental improvement over existing methods.
The paper tackles the problem of enabling users to effectively control and critically evaluate collaboration among multiple domain-expert agents in multi-agent systems for research ideation, finding that Perspectra significantly increased critical-thinking behaviors, interdisciplinary replies, and proposal revisions compared to a baseline.
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.