LensAgent: A Self Evolving Agent for Autonomous Physical Inference of Sub-galactic Structure

TL;DR

LensAgent is a novel autonomous framework using large language models to infer sub-galactic mass distributions from strong lensing data, overcoming previous scalability and degeneracy issues.

Contribution

It introduces a training-free, LLM-driven agentic system that combines reasoning with physical modeling for scalable substructure inference.

Findings

Successfully reconstructed mass distributions in strong lensing systems.

Enabled robust extraction of sub-galactic substructures at scale.

Demonstrated potential for cosmological studies with upcoming surveys.

Abstract

Probing dark matter distribution on sub-galactic scales is essential for testing the Cold Dark Matter ($\Lambda$CDM) paradigm. Strong gravitational lensing, as one of the most powerful approach by far, provides a direct, purely gravitational probe of these substructures. However, extracting cosmological constraints is severely bottlenecked by the mass-sheet degeneracy (MSD) and the unscalable nature of manual and neural-network modeling. Here, we introduce LensAgent, a pioneering training-free, large language model (LLM)-driven agentic framework for the autonomous physical inference of mass distributions. Operating as an autonomous scientific agent, LensAgent couples high-level logical reasoning with deterministic physical modeling tools, demonstarting successful reconstruction of mass distribution in SLACS Grade A strong lensing systems. This self-evolving architecture enables the robust extraction of sub-galactic substructures at scale, unlocking the cosmological potential of upcoming wide-field surveys such as the Rubin Observatory (LSST) and Euclid.