发表机构
College of AI, Tsinghua University; Shanghai Qizhi Institute; Business School, Renmin University of China; School of Physics, Beihang University; School of Information and Software Engineering, University of Electronic Science and Technology of China; Behavioral and Cognitive Neuroscience Center, Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University; College of Engineering, Georgia Institute of Technology; School of Life Sciences & IDG/McGovern Institute for Brain Research, Tsinghua University; School of Computing and Artificial Intelligence, Southwest Jiaotong University; Weixian College, Tsinghua University; Department of Psychological and Cognitive Sciences, Tsinghua University（清华大学人工智能学院; 上海期智研究院; 中国人民大学商学院; 北京航空航天大学物理学院; 电子科技大学信息与软件工程学院; 复旦大学脑科学与智能技术研究院行为与认知神经科学中心; 佐治亚理工学院工程学院; 清华大学生命科学学院&清华-IDG/麦戈文脑科学研究院; 西南交通大学计算机与人工智能学院; 清华大学未央学院; 清华大学心理学与认知科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对脑科学研究整合证据难、人工智能代理有缺陷的问题，提出完全开源的多智能体系统BrainPilot，它有可追溯日志和验证结果，含知识库与技能库，经实验评估，其开源模型以低成本达先进框架性能。
AI 中文摘要
理解大脑越来越依赖跨尺度、模态和学科整合证据。解决单个研究问题需要一系列协调操作。人工智能代理有望加速这一过程，但当前代理在脑科学领域缺乏专业知识，可能编造主张，在多步推理中偏离，且专家干预点少。我们提出了BrainPilot，一个完全开源的多智能体系统，它通过可追溯的日志和经智能体验证的结果加速脑科学研究。主要研究者（PI）智能体协调基于精心策划的领域知识的专家智能体，包括一个包含7233个索引条目的统一脑科学知识库和一个涵盖七个研究领域的72个可重复使用方法单元的技能库。每个主要步骤都记录在追踪图中，审核智能体将伪造检查集成到工作流程中。为了评估，我们运行了来自智能体期末考试的三个脑科学任务，引入了自己的基准BrainPilotBench-v0，并展示了其他端到端案例研究。在这些评估中，具有开源主干模型的BrainPilot以更低成本实现了与最先进智能体框架相当的性能。
英文摘要
Understanding the brain increasingly depends on integrating evidence across scales, modalities, and disciplines. Addressing a single research question therefore requires a coordinated sequence of operations, from surveying prior work to executing analyses and interpreting results in light of domain knowledge. AI agents promise to accelerate this process, but current agents lack domain expertise in brain science, may fabricate claims, drift during multi-step reasoning, and offer few defined points for expert intervention. These failures are especially costly in brain science, where conclusions feed into downstream scientific claims and depend on laboratory-specific expertise and careful human judgment. We present \textbf{BrainPilot} a \textbf{fully open-source} multi-agent system that accelerates brain science research with traceable logs and agent-verified results. A principal investigator (PI) agent coordinates specialist agents grounded in curated domain knowledge: a unified brain science knowledge base containing 7{,}233 indexed items and a skill library of 72 reusable methodology units across seven research domains. Every major step is recorded in the Graph of Trace, an auditable record that links subgoals, tool use, evidence, and claims and allows researchers to follow and inspect the workflow. An Auditor agent further integrates fabrication checking into the workflow. For evaluation, we run three brain science tasks from Agents' Last Exam, introduce our own benchmark, \textbf{BrainPilotBench-v0}, and present additional end-to-end case studies. Across these evaluations, BrainPilot with an open-source backbone model attains performance comparable to state-of-the-art agent framework with less costs.
