Bridging Literature and the Universe Via A Multi-Agent Large Language Model System

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xiaowen, Bi, Zhenyu, Lachance, Patrick, Wang, Xuan, Di Matteo, Tiziana, Croft, Rupert A. C.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918096835444736
author Zhang, Xiaowen
Bi, Zhenyu
Lachance, Patrick
Wang, Xuan
Di Matteo, Tiziana
Croft, Rupert A. C.
author_facet Zhang, Xiaowen
Bi, Zhenyu
Lachance, Patrick
Wang, Xuan
Di Matteo, Tiziana
Croft, Rupert A. C.
contents As cosmological simulations and their associated software become increasingly complex, physicists face the challenge of searching through vast amounts of literature and user manuals to extract simulation parameters from dense academic papers, each using different models and formats. Translating these parameters into executable scripts remains a time-consuming and error-prone process. To improve efficiency in physics research and accelerate the cosmological simulation process, we introduce SimAgents, a multi-agent system designed to automate both parameter configuration from the literature and preliminary analysis for cosmology research. SimAgents is powered by specialized LLM agents capable of physics reasoning, simulation software validation, and tool execution. These agents collaborate through structured communication, ensuring that extracted parameters are physically meaningful, internally consistent, and software-compliant. We also construct a cosmological parameter extraction evaluation dataset by collecting over 40 simulations in published papers from Arxiv and leading journals that cover diverse simulation types. Experiments on the dataset demonstrate a strong performance of SimAgents, highlighting its effectiveness and potential to accelerate scientific research for physicists. Our demonstration video is available at: https://youtu.be/w1zLpm_CaWA. The complete system and dataset are publicly available at https://github.com/xwzhang98/SimAgents.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08958
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging Literature and the Universe Via A Multi-Agent Large Language Model System
Zhang, Xiaowen
Bi, Zhenyu
Lachance, Patrick
Wang, Xuan
Di Matteo, Tiziana
Croft, Rupert A. C.
Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
Artificial Intelligence
Multiagent Systems
As cosmological simulations and their associated software become increasingly complex, physicists face the challenge of searching through vast amounts of literature and user manuals to extract simulation parameters from dense academic papers, each using different models and formats. Translating these parameters into executable scripts remains a time-consuming and error-prone process. To improve efficiency in physics research and accelerate the cosmological simulation process, we introduce SimAgents, a multi-agent system designed to automate both parameter configuration from the literature and preliminary analysis for cosmology research. SimAgents is powered by specialized LLM agents capable of physics reasoning, simulation software validation, and tool execution. These agents collaborate through structured communication, ensuring that extracted parameters are physically meaningful, internally consistent, and software-compliant. We also construct a cosmological parameter extraction evaluation dataset by collecting over 40 simulations in published papers from Arxiv and leading journals that cover diverse simulation types. Experiments on the dataset demonstrate a strong performance of SimAgents, highlighting its effectiveness and potential to accelerate scientific research for physicists. Our demonstration video is available at: https://youtu.be/w1zLpm_CaWA. The complete system and dataset are publicly available at https://github.com/xwzhang98/SimAgents.
title Bridging Literature and the Universe Via A Multi-Agent Large Language Model System
topic Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2507.08958