Pith. sign in

REVIEW 5 cited by

Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.14807 v2 pith:7F5CNDHO submitted 2024-09-23 astro-ph.IM astro-ph.GA

classification astro-ph.IMastro-ph.GA
keywords mephistoobservationsresearchagentsastronomicalgalaxiesgalaxyinterpret
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

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

    astro-ph.IM 2025-07 conditional novelty 6.0 of 10

    A multi-agent large language model system extracts cosmological simulation parameters from published papers and generates valid MP-GADGET configuration files, achieving 98.7% micro-F1 on a new 41-simulation benchmark.

  2. Zangetsu: A Candidate of Isolated, Quiescent, and Backsplash Ultra-Diffuse Galaxy in the COSMOS Field

    astro-ph.GA 2025-05 conditional novelty 6.0 of 10

    A candidate ultra-diffuse galaxy, Zangetsu, found in HSC COSMOS images is unusually elongated, quiescent, apparently isolated, and an extreme size outlier.

  3. Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation

    astro-ph.IM 2025-01 conditional novelty 6.0 of 10

    A multi-survey CNN estimates photometric redshifts from GALEX, PanSTARRS, and UnWISE cutouts, with early and late image fusion performing comparably.

  4. Multi-Agent System for Cosmological Parameter Analysis

    astro-ph.IM 2024-11 conditional novelty 6.0 of 10

    A multi-agent LLM system with retrieval and local code execution reproduced ACT DR6 lensing cosmological parameter constraints without human-written code, and generalized to two research-software tasks.

  5. AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model

    astro-ph.IM 2024-11 conditional novelty 6.0 of 10

    A specialized 8B-parameter language model trained on astronomy literature and synthetic Q&A matches GPT-4o on the AstroMLab-1 astronomy benchmark at a fraction of the cost.

Pith tools