AstroGenesis：面向天体物理研究的领域专用多智能体人工智能
AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research
浏览论文内容
中文总结 AI 辅助
AstroGenesis是一个领域专用多智能体AI框架，整合文献检索、多波段数据分析和理论建模，用于天体物理研究，并在耀变体研究中验证了其有效性。
中文摘要 AI 辅助
现代天体物理研究需要整合快速扩展的科学文献、异构观测数据以及日益复杂的物理模型。我们介绍了AstroGenesis（https://this URL），一个领域专用的多智能体人工智能框架，将文献检索、多波段数据访问与分析、理论建模和研究构思整合在一个统一的研究工作流中。当前实现聚焦于耀变体研究，由监督智能体和规划器/重规划器架构协调专门化智能体。这些智能体提供检索和综合文献、访问和分析多波段观测、执行物理建模以及识别研究方向的能力。核心组件是理论建模智能体，它利用预训练的神经网络替代模型，通过自然语言交互实现高效的宽带和多信使建模。该框架通过多阶段检索和排序流水线，提供对科学就绪的多波段观测数据和基于检索的文献的自然语言访问。文献检索系统使用两个基准进行评估：单论文基准，其中每个问题针对一篇出版物；多论文基准，其中问题可能需要来自多篇出版物的证据。在单论文问题的前五个结果中，至少检索到一篇相关出版物的比例为76.6%，多论文问题的比例为79.2%。代表性工作流展示了如何在可追溯的分析中结合文献、观测数据、物理建模和假设生成。该框架可扩展到其他天体物理领域，旨在简化研究工作流，实现高效、关联且可复现的科学调查。
英文摘要
Modern astrophysical research requires the integration of rapidly expanding scientific literature, heterogeneous observational data, and increasingly complex physical models. We introduce AstroGenesis (https://astrogenai.com), a domain-specific multi-agent AI framework that integrates literature retrieval, multiwavelength data access and analysis, theoretical modeling, and research ideation within a unified research environment.The current implementation focuses on blazar research, with specialized agents coordinated by a Supervisor Agent and Planner/Replanner architecture. These agents provide capabilities for retrieving and synthesizing literature, accessing and analyzing multiwavelength observations, performing physical modeling, and identifying research directions. A central component is the Theoretical Modeling Agent, which uses pretrained neural-network surrogate models to enable efficient broadband and multimessenger modeling through natural-language interaction. The framework provides natural-language access to science-ready multiwavelength observational data and retrieval-grounded literature through a multi-stage retrieval and ranking pipeline. The literature-retrieval system was evaluated using two benchmarks: a single-paper benchmark, in which each question targets one publication, and a multi-paper benchmark, in which questions may require evidence from several publications. At least one relevant publication was retrieved among the top five results for 76.6% of the single-paper questions and 79.2% of the multi-paper questions. Representative workflows demonstrate how literature, observational data, physical modeling, and hypothesis generation can be combined within traceable analyses. The framework is extensible to additional astrophysical domains, with the goal of streamlining research workflows and enabling efficient, connected, and reproducible scientific investigations.
发表机构
- ICRANet-Armenia（亚美尼亚国际中心天体物理与相对论）
- California Institute of Technology（加州理工学院）
- Eureka Scientific（尤里卡科学公司）
- Department of Physics, The George Washington University（乔治华盛顿大学物理系）
- Department of Physics, Bar-Ilan University（巴伊兰大学物理系）
- INAF, Osservatorio Astronomico di Brera（意大利国家天体物理研究所布雷拉天文台）
- Center for Astrophysics and Space Science (CASS), New York University Abu Dhabi（纽约大学阿布扎比分校天体物理学与空间科学中心）
机构由 AI 辅助整理，请以论文原文为准。
