Searching for BSM Experimental Signatures with Large Lagrangian Models

2026-09-29

AI Summary

This study addresses the limitation that physics beyond the Standard Model remains constrained by a lack of discriminative experimental observations. To this end, it proposes the hAIthem framework, which pioneers the integration of reinforcement learning-based autonomous exploration with the physical knowledge embedded in large language models. Built upon an autoregressive Transformer architecture and a phenomenological toolchain, the framework automatically searches high-dimensional Lagrangian parameter spaces for unexcluded theoretical regions and distinctive experimental signatures, thereby achieving an end-to-end closed loop from theory generation to signal discovery. Proof-of-concept experiments demonstrate that its reinforcement learning search strategy significantly outperforms evolutionary algorithm baselines. Furthermore, the framework identifies novel and viable combinations of experimental observables within dark matter 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.

Problem

• Beyond the Standard Model
• dark matter
• experimental signatures
• parameter space exploration
• observable discovery

Innovation

• Large Lagrangian Model
• Reinforcement Learning
• Large Language Models
• Beyond the Standard Model
• Autoregressive Transformer