发表机构
Shanghai Artificial Intelligence Laboratory; Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences; The Chinese University of Hong Kong; Southeast University; Fudan University; New York University（上海人工智能实验室; 中国科学院脑科学与智能技术卓越创新中心; 香港中文大学; 东南大学; 复旦大学; 纽约大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SeekBrain是用于加速神经科学发现的自主多智能体框架，通过分层规划与跨模态分析生成分析流程，在BrainArena基准上优于现有智能体，实际研究中成功揭示了斑马鱼与小鼠的神经表征规律。
AI 中文摘要
现代神经科学依赖于整合多尺度、多模态数据集，以揭示支撑智能的神经原理。然而，高度异质的数据和碎片化的工作流带来的分析挑战日益限制了发现进程。本文介绍SeekBrain，这是一个自主多智能体框架，旨在通过基于领域的分层规划和跨模态数据分析加速神经科学发现。SeekBrain动态构建从代码-论文对中提取的分析方案库，通过将这种编码的专业知识与智能体规划和执行引擎相结合，该框架可按需规模化生成假设和分析流程。在专家标注的BrainArena基准上的系统评估表明，SeekBrain在各类分析任务中大幅优于最先进的智能体基线。关键的是，在实际研究部署中，SeekBrain整合了行为、神经和解剖学数据，揭示了幼体斑马鱼行为的结构化分布式神经表征，以及小鼠决策任务中全脑区域解码强度的共享轴。这些结果证实，SeekBrain是一种可扩展且实用的工具，可加速神经科学领域的数据驱动发现。
英文摘要
Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytical challenges posed by highly heterogeneous data and fragmented workflows increasingly constrain discoveries. Here we introduce SeekBrain, an autonomous multi-agent framework designed to accelerate neuroscience discovery through domain-grounded hierarchical planning and cross-modal data analysis. SeekBrain dynamically constructs a repertoire of analysis recipes extracted from code-paper pairs. By coupling this codified expertise with agentic planning and execution engines, the framework scalably generates hypotheses and analytical pipelines on demand. Systematic evaluation on the expert-annotated BrainArena benchmark demonstrates that SeekBrain substantially outperforms state-of-the-art agent baselines across various analysis tasks. Crucially, when deployed in real-world research, SeekBrain integrated behavioral, neural, and anatomical data to reveal structured, distributed neural representations of larval zebrafish behavior and a shared axis of regional decoding strength across the brain in a mouse decision-making task. These results establish SeekBrain as a scalable and practical tool for accelerating data-driven discoveries in neuroscience.
