Searching for BSM Experimental Signatures with Large Lagrangian Models
Abstract
The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating experimental observations. A case in point is dark matter, where the overwhelming gravitational evidence only goes so far in distinguishing between models within a vast theory space. Exploring the space of testable model signatures may help identify overlooked experimental observables and indicate the utility of future experiments. A challenge is designing a search through model signatures outside what is found in the literature. Our primary contribution is hAIthem, a framework that combines the self-guided exploration of reinforcement learning (RL) with the broad literature-derived knowledge of LLMs. We build an RL agent that learns to find which portions of a theory's high-dimensional parameter space are not excluded under some subset of constraints by playing a Battleship-style "game" against a suite of phenomenology tools. The agent is built as a Large Lagrangian Model (LLaM), an autoregressive transformer that reads a tokenized Lagrangian, is pretrained at scale (here on ~1 billion tokens from ~10,000 Lagrangians), and is fine-tuned in a live environment. The framework then constructs a decision tree that separates RL-found regions using observables computed with established tools, and passes the remaining degenerate regions to a set of LLM agents that compete to produce realistic signatures. In this proof of concept, RL-search outperforms an evolutionary-algorithm baseline, finding more viable regions with greater physical diversity. In a restricted space of single dark scalar multiplet models, we find that hAIthem proposes interesting combinations of previously studied observables, such as the application of a halo-independent kinematic ratio to paleo-detectors.
Related
- Searching for signatures of self-interacting dark matter in halos from full physics simulations: From 3D structure to projected observables
- Sown at Cosmic Dawn: Searching for Pop III Signatures in JWST JADES He II Selected Line Emitters
- Searching for Signatures of i-process Nucleosynthesis in Metal-Rich, Lead-rich Barium Stars
- Statistics of large-scale structure from the transition probability of Lagrangian trajectories
- Black hole-neutron star binaries with high spins and large mass asymmetries: III. Properties of the ejected material and its electromagnetic signatures
BibTeX
@misc{elsharkawy2026searching,
title = {{Searching for BSM Experimental Signatures with Large Lagrangian Models}},
author = {Ibrahim Elsharkawy and Victoria Knapp-Perez and Wahid Bhimji and Aishik Ghosh},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38309},
eprint = {2609.38309},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38309},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Searching for BSM Experimental Signatures with Large Lagrangian Models
AU - Ibrahim Elsharkawy
AU - Victoria Knapp-Perez
AU - Wahid Bhimji
AU - Aishik Ghosh
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38309
UR - https://arxiv.org/abs/2609.38309
AB - The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating experimental observations. A case in point is dark matter, where the overwhelming gravitational evidence only goes so far in distinguishing between models within a vast theory space. Exploring the space of testable model signatures may help identify overlooked experimental observables and indicate the utility of future experiments. A challenge is designing a search through model signatures outside what is found in the literature. Our primary contribution is hAIthem, a framework that combines the self-guided exploration of reinforcement learning (RL) with the broad literature-derived knowledge of LLMs. We build an RL agent that learns to find which portions of a theory's high-dimensional parameter space are not excluded under some subset of constraints by playing a Battleship-style "game" against a suite of phenomenology tools. The agent is built as a Large Lagrangian Model (LLaM), an autoregressive transformer that reads a tokenized Lagrangian, is pretrained at scale (here on ~1 billion tokens from ~10,000 Lagrangians), and is fine-tuned in a live environment. The framework then constructs a decision tree that separates RL-found regions using observables computed with established tools, and passes the remaining degenerate regions to a set of LLM agents that compete to produce realistic signatures. In this proof of concept, RL-search outperforms an evolutionary-algorithm baseline, finding more viable regions with greater physical diversity. In a restricted space of single dark scalar multiplet models, we find that hAIthem proposes interesting combinations of previously studied observables, such as the application of a halo-independent kinematic ratio to paleo-detectors.
ER -