Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913973794766848 |
|---|---|
| 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 traditionally relies on extensive domain knowledge to interpret observations and narrow down hypotheses. We demonstrate that this process can be emulated using large language model-based agents to accelerate research workflows. We propose mephisto, a multi-agent collaboration framework that mimics human reasoning to interpret multi-band galaxy observations. mephisto interacts with the CIGALE codebase, which includes spectral energy distribution (SED) models to explain observations. In this open-world setting, mephisto learns from its self-play experience, performs tree search, and accumulates knowledge in a dynamically updated base. As a proof of concept, we apply mephisto to the latest data from the James Webb Space Telescope. mephisto attains near-human proficiency in reasoning about galaxies' physical scenarios, even when dealing with a recently discovered population of "Little Red Dot" galaxies. This represents the first demonstration of agentic research in astronomy, advancing towards end-to-end research via LLM agents and potentially expediting astronomical discoveries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14807 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents Sun, Zechang Ting, Yuan-Sen Liang, Yaobo Duan, Nan Huang, Song Cai, Zheng Instrumentation and Methods for Astrophysics Astrophysics of Galaxies Astronomical research traditionally relies on extensive domain knowledge to interpret observations and narrow down hypotheses. We demonstrate that this process can be emulated using large language model-based agents to accelerate research workflows. We propose mephisto, a multi-agent collaboration framework that mimics human reasoning to interpret multi-band galaxy observations. mephisto interacts with the CIGALE codebase, which includes spectral energy distribution (SED) models to explain observations. In this open-world setting, mephisto learns from its self-play experience, performs tree search, and accumulates knowledge in a dynamically updated base. As a proof of concept, we apply mephisto to the latest data from the James Webb Space Telescope. mephisto attains near-human proficiency in reasoning about galaxies' physical scenarios, even when dealing with a recently discovered population of "Little Red Dot" galaxies. This represents the first demonstration of agentic research in astronomy, advancing towards end-to-end research via LLM agents and potentially expediting astronomical discoveries. |
| title | Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents |
| topic | Instrumentation and Methods for Astrophysics Astrophysics of Galaxies |
| url | https://arxiv.org/abs/2409.14807 |