Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Zechang, Ting, Yuan-Sen, Liang, Yaobo, Duan, Nan, Huang, Song, Cai, Zheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914084116496384
author Sun, Zechang
Ting, Yuan-Sen
Liang, Yaobo
Duan, Nan
Huang, Song
Cai, Zheng
author_facet Sun, Zechang
Ting, Yuan-Sen
Liang, Yaobo
Duan, Nan
Huang, Song
Cai, Zheng
contents Astronomical research has long relied on human expertise to interpret complex data and formulate scientific hypotheses. In this study, we introduce Mephisto -- a multi-agent collaboration framework powered by large language models (LLMs) that emulates human-like reasoning for analyzing multi-band galaxy observations. Mephisto interfaces with the CIGALE codebase (a library of spectral energy distribution, SED, models) to iteratively refine physical models against observational data. It conducts deliberate reasoning via tree search, accumulates knowledge through self-play, and dynamically updates its knowledge base. Validated across diverse galaxy populations -- including the James Webb Space Telescope's recently discovered "Little Red Dot" galaxies -- we show that Mephisto demonstrates proficiency in inferring the physical properties of galaxies from multi-band photometry, positioning it as a promising research copilot for astronomers. Unlike prior black-box machine learning approaches in astronomy, Mephisto offers a transparent, human-aligned reasoning process that integrates seamlessly with existing research practices. This work underscores the possibility of LLM-driven agent-based research for astronomy, establishes a foundation for fully automated, end-to-end artificial intelligence (AI)-powered scientific workflows, and unlocks new avenues for AI-augmented discoveries in astronomy.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations
Sun, Zechang
Ting, Yuan-Sen
Liang, Yaobo
Duan, Nan
Huang, Song
Cai, Zheng
Instrumentation and Methods for Astrophysics
Astrophysics of Galaxies
Astronomical research has long relied on human expertise to interpret complex data and formulate scientific hypotheses. In this study, we introduce Mephisto -- a multi-agent collaboration framework powered by large language models (LLMs) that emulates human-like reasoning for analyzing multi-band galaxy observations. Mephisto interfaces with the CIGALE codebase (a library of spectral energy distribution, SED, models) to iteratively refine physical models against observational data. It conducts deliberate reasoning via tree search, accumulates knowledge through self-play, and dynamically updates its knowledge base. Validated across diverse galaxy populations -- including the James Webb Space Telescope's recently discovered "Little Red Dot" galaxies -- we show that Mephisto demonstrates proficiency in inferring the physical properties of galaxies from multi-band photometry, positioning it as a promising research copilot for astronomers. Unlike prior black-box machine learning approaches in astronomy, Mephisto offers a transparent, human-aligned reasoning process that integrates seamlessly with existing research practices. This work underscores the possibility of LLM-driven agent-based research for astronomy, establishes a foundation for fully automated, end-to-end artificial intelligence (AI)-powered scientific workflows, and unlocks new avenues for AI-augmented discoveries in astronomy.
title Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations
topic Instrumentation and Methods for Astrophysics
Astrophysics of Galaxies
url https://arxiv.org/abs/2510.08354