通过角色化协作与可视化论坛，提升多智能体研究构思中的批判性思维。
Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation
- 设计论坛式交互界面，支持@邀请专家、分线讨论与实时思维导图。
- 18人实验显示批判性行为频率和深度显著提升，提案修订更频繁。
- 适合需要跨学科论证与深度思辨的研究者使用。
近年来，多智能体系统（MAS）通过赋予智能体角色实现信息检索与创意生成。然而，用户如何有效控制、引导并批判性评估多个领域专家智能体的协作仍缺乏研究。我们提出Perspectra，一种基于论坛界面的交互式多智能体系统，通过@提及机制邀请特定智能体、分线并行探索，并以实时思维导图可视化论点与推理过程。在包含18名参与者的组内实验中，相比传统群聊基线，Perspectra显著提升了批判性思维行为的频率与深度，激发更多跨学科回应，并导致更高频的提案修订。研究讨论了通过支持用户对多智能体对抗性对话的控制，来设计能促进批判性思维的多智能体工具的启示。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。