AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research
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.
Related
- Multi-Model Analysis of the Astrophysical S(E) Factor for the 9Be(p,α)6Li Reaction and Its Impact on Astrophysical Reaction Rates
- Xenia: A Table-Driven Code for Astrophysical Multi-Fluid Hydrodynamics
- Hunting for Compact Object Binaries from eRASS1 Optical Counterparts through ZTF Time-domain Photometry and Multi-wavelength Surveys
- Atmosphere mitigation in CMB observations using multi-frequency time-domain component separation
- Simultaneous Real-Color Time-Domain Survey of the Coma Field with the Multi-channel Photometric Survey Telescope (Mephisto)
BibTeX
@misc{sahakyan2026astrogenesis,
title = {{AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research}},
author = {N. Sahakyan and M. Khachatryan and A. Mahabal and D. Pasham and A. Khachatryan and V. Markosyan and N. Unkovskii and V. Vardanyan and D. Bégué and P. Giommi and G. Harutyunyan and D. Israyelyan and A. Tramacere and A. Casotto and Y. Wang and D. Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28579},
eprint = {2609.28579},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28579},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research
AU - N. Sahakyan
AU - M. Khachatryan
AU - A. Mahabal
AU - D. Pasham
AU - A. Khachatryan
AU - V. Markosyan
AU - N. Unkovskii
AU - V. Vardanyan
AU - D. Bégué
AU - P. Giommi
AU - G. Harutyunyan
AU - D. Israyelyan
AU - A. Tramacere
AU - A. Casotto
AU - Y. Wang
AU - D. Li
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.28579
UR - https://arxiv.org/abs/2609.28579
AB - 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.
ER -