Saved in:
Bibliographic Details
Main Authors: Feng, Xiaotang, Wang, Zihan, Shu, Zilang, Kneib, Jean-Paul, Torr, Philip
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03691
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911567722840064
author Feng, Xiaotang
Wang, Zihan
Shu, Zilang
Kneib, Jean-Paul
Torr, Philip
author_facet Feng, Xiaotang
Wang, Zihan
Shu, Zilang
Kneib, Jean-Paul
Torr, Philip
contents Probing dark matter distribution on sub-galactic scales is essential for testing the Cold Dark Matter ($Λ$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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03691
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LensAgent: A Self Evolving Agent for Autonomous Physical Inference of Sub-galactic Structure
Feng, Xiaotang
Wang, Zihan
Shu, Zilang
Kneib, Jean-Paul
Torr, Philip
Astrophysics of Galaxies
Instrumentation and Methods for Astrophysics
Probing dark matter distribution on sub-galactic scales is essential for testing the Cold Dark Matter ($Λ$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.
title LensAgent: A Self Evolving Agent for Autonomous Physical Inference of Sub-galactic Structure
topic Astrophysics of Galaxies
Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2604.03691