用多智能体论坛让人类与AI共同探索科学问题，拓宽思路。
AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions
- 多个异构智能体异步讨论科学问题，模拟论坛对话。
- 用户可提交问题、筛选想法、追问细节，生成总结报告。
- 65%用户认为它比单个大模型更适合作为早期探索工具。
科学创意的发现仍是研究中的关键挑战。当前研究者多依赖小范围讨论或与单一大语言模型交互，易受限于视角狭窄。本文提出AgentPanel，一种支持人-机协作的多智能体科学探索论坛。异构智能体在论坛式环境中异步讨论科学问题，研究人员可提交问题、浏览并组织候选想法、与智能体互动追问，还可生成事后总结报告。我们从创意质量、探索广度、交互效率、候选选择效率和实际可用性五个维度评估该系统。离线实验显示，AgentPanel优于集中式多智能体辩论基线。20名参与者的人类研究进一步表明，用户高度认可其视角多样性与探索支持能力。相较于常用LLM工具，65%的参与者认为AgentPanel在研究方向广度和整体适用性上表现更优。平台已公开：https://agentpanel.cc/。
原文摘要 · Abstract (English)
Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration. Heterogeneous agents asynchronously discuss scientific questions in a forum-style environment, while researchers can submit questions, browse and organize candidate ideas, engage agents in follow-up interactions, and optionally generate post-hoc summary reports. We evaluate AgentPanel in terms of idea quality, exploration breadth, interaction effectiveness, candidate-selection efficiency, and practical utility. Offline experiments show that AgentPanel outperforms a centralized multi-agent debate baseline. A human study with 20 participants further shows that users value AgentPanel for perspective diversity and exploration support. In experience-based comparisons with commonly used LLM tools, 65\% of participants favored AgentPanel for both breadth of research directions and overall suitability for early-stage exploration. The platform is publicly available at https://agentpanel.cc/.
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。