AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research

arXiv:2609.28579 · astro-ph.IM, astro-ph.GA, astro-ph.HE · Submitted 2026-09-23 · Read on arXiv

astro-ph.IM, astro-ph.GA, astro-ph.HE

Submitted: 2026-09-23

Updated: 2026-09-23

Comments: Submitted to ApJ; AstroGenesis demo: https://youtube.com/shorts/vsfZ_D_XcJU

Code: https://github.com/redis/redis

License: http://creativecommons.org/licenses/by/4.0/

The gist: Modern astrophysical research requires the integration of rapidly expanding scientific literature, heterogeneous observational data, and increasingly complex physical models.

Terminology

Abstract

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.

Sources

Related papers