Search arXiv⌕ Search

arXiv · 2609.38309

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.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ibrahim Elsharkawy, Victoria Knapp-Perez, Wahid Bhimji, Aishik Ghosh. 2026-09-29. Searching for BSM Experimental Signatures with Large Lagrangian Models. https://arxiv.org/abs/2609.38309

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Pomeron Weights in QCD Processes at High Energy and the $S$-Matrix Unitarity Constraint

The pomeron topological cross-section is derived for the eikonal and the $U$-matrix unitarization schemes using a generalized representation of the scattering amplitude at high energy in an effort to examine pomeron characteristics, namely the multiplicity distribution, fluctuation, and correlation, and to reveal the impact of pomeron weights on the $pp$ multiplicity distribution. The results demonstrate that the $U$-matrix inherently incorporates a larger amount of diffraction production into the multi-pomeron vertices, yielding a larger pomerons' variability regardless of the energy range, while such fluctuations become significant only beyond a specific high-energy threshold in eikonal-like schemes. Most importantly, our findings indicate that within the $U$-matrix scheme, an increase in exchanged pomerons results in more pronounced pomeron correlations and that this correlated resummation plays a key role in enhancing multi-parton collisions. We argue that the choice of unitarization scheme is not arbitrary, as it directly dictates the statistical structure of multi-reggeon exchanges. By reflecting the composite nature of hadrons, rational alternatives to eikonal-like schemes, such as the $U$-matrix, offer a compelling theoretical foundation for modeling high-energy hadronic collisions, provided that specific formulations can be identified that strictly satisfy all mathematical and physical constraints.

hep-ph↗

Two-loop renormalisation of quark and gluon fields in the SMEFT

We compute the contributions of CP-conserving operators in the dimension-six SMEFT to the two-loop renormalisation constants of quark and gluon fields in the $\overline{\textrm{MS}}$-scheme. Specifically, we consider the top-quark chromomagnetic operator and the triple gluon operator. We work with the background-field method, which allows us to extract the contribution of these operators to the two-loop running of the top mass and the strong coupling constant. We discuss in detail the mixing with the unphysical operators required for the renormalisation, and we present analytic results for the renormalisation constants of all relevant operators.

hep-ph↗

Two-loop renormalisation of quark and gluon fields in the SMEFT in the on-shell scheme

We compute the contributions of CP-conserving dimension-six SMEFT operators to the two-loop renormalisation constants of quark and gluon fields in the on-shell scheme. Specifically, we consider the top-quark chromomagnetic operator and the triple gluon operator. We also compute the contribution of four-quark operators to the gluon renormalisation constant and discuss the implications for the running of the strong coupling constant.

hep-ph↗