aiqbench analysis
This research applies a reinforcement learning agent, specifically a Large Lagrangian Model (LLaM), to navigate the vast parameter space of physics theories beyond the Standard Model. By combining self-guided exploration with knowledge derived from large language models, the framework successfully identifies viable experimental signatures that traditional methods might overlook. This demonstrates a practical integration of advanced AI techniques into high-energy physics phenomenology to enhance discovery potential.
Searching for BSM Experimental Signatures with Large Lagrangian Models
arXiv:2609.38309v1 Announce Type: cross 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.
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.
High Energy Physics - Phenomenology (hep-ph); Cosmology and Nongalactic Astrophysics (astro-ph.CO); Artificial Intelligence (cs.AI); High Energy Physics - Experiment (hep-ex)
arXiv:2609.38309 [hep-ph]
(or arXiv:2609.38309v1 [hep-ph] for this version)
https://doi.org/10.48550/arXiv.2609.38309 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 304 words
Related coverage
Quantum muonium experiment could beat existing dark matter limits
Quantum Zeitgeist · Sep 11, 2026
Large Hadron Collider search rules out quantum black holes with certain properties
Quantum Zeitgeist · Sep 19, 2026
Links #5: 2026/07
LessWrong · Jul 31, 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · Oct 8, 2026