ACAT 2025

Using Large Language Models to Accelerate Access to Physics

Not scheduled

2h 40m

Hamburg, Germany

Oral Track 1: Computing Technology for Physics Research Track 1: Computing Technology for Physics Research

Speaker

Gordon Watts (University of Washington (US))

Description

In high energy physics, most AI/ML efforts focus on improving the scientific process itself — modeling, classification, reconstruction, and simulation. In contrast, we explore how Large Language Models (LLMs) can accelerate access to the physics by assisting with the broader ecosystem of work that surrounds and enables scientific discovery. This includes understanding complex documentation, navigating experimental frameworks, writing and debugging code, generating visualizations, and interacting with APIs and databases.

We present an evolving suite of tools that apply LLMs in support roles across this ecosystem. Building on prior work using Retrieval-Augmented Generation (RAG) to query the large particle physics scientific collections, we now incorporate advances such as the Model Context Protocol for better grounding, agent-based orchestration for multi-step reasoning and task execution, entity scanning for rapid information extraction, and live code generation tailored to experimental workflows. Our LLM-driven systems no longer operate as isolated tools but as participants in an integrated physics infrastructure.

We report on system design, model performance, and real-world use cases, and we outline open challenges around evaluation, and reliability. Many pieces and communication APIs are being standardized, but a great deal of work remains to make these useful in particle physics. By focusing on how LLMs can streamline the path to doing physics, this work explores this space of AI assistance.

Significance

The first version of this work, shown in NY, was a simple RAG system. Using LLMs to extract concepts and using a graph of relationships between concepts already dramatically improves the LLM's ability to discuss documents. Further, it is now easy to integrate live information into an LLM (calling tools) - something that wasn't truely supported before. Finally, the appearance of open-source agents - like agents that write code and test it - means we can start to talk seriously about agents that write EPE code. There is a lot of work to do to put these pieces together, however.