# GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation

arXiv: https://arxiv.org/abs/2602.15039 · HTML: https://mlsanity.com/paper/2602.15039/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 7 of 7)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [A multi-agentic framework for real-time, autonomous freeform metasurface design](https://mlsanity.com/paper/2503.20479/) (2025)
- [Automating High Energy Physics Data Analysis with LLM-Powered Agents](https://mlsanity.com/paper/2512.07785/) (2025)
- [Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator](https://mlsanity.com/paper/2509.17255/) (2025)
- [GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols](https://mlsanity.com/paper/2512.06404/) (2025)

## Built on by (most cited first, 6 of 6)

- [AI Agents Can Already Autonomously Perform Experimental High Energy Physics](https://mlsanity.com/paper/2603.20179/) (2026)
- [PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research](https://mlsanity.com/paper/2604.15411/) (2026)
- [PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language](https://mlsanity.com/paper/2607.09789/) (2026)
- [Machine learning for the LHC physics program: a 2025-2026 stocktake](https://mlsanity.com/paper/2609.32874/) (2026)
- [NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents](https://mlsanity.com/paper/2610.03631/) (2026)
- [Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery](https://mlsanity.com/paper/2610.12293/) (2026)

## Abstract (arXiv)

We present GRACE, a simulation-native agent for autonomous experimental design in high-energy and nuclear physics. Given multimodal input in the form of a natural-language prompt or a published experimental paper, the agent extracts a structured representation of the experiment, constructs a runnable toy simulation, and autonomously explores design modifications using first-principles Monte Carlo methods. Unlike agentic systems focused on operational control or execution of predefined procedures, GRACE addresses the upstream problem of experimental design: proposing non-obvious modifications to detector geometry, materials, and configurations that improve physics performance under physical and practical constraints. The agent evaluates candidate designs through repeated simulation, physics-motivated utility functions, and budget-aware escalation from fast parametric models to full Geant4 simulations, while maintaining strict reproducibility and provenance tracking. We demonstrate the framework on historical experimental setups, showing that the agent can identify optimization directions that align with known upgrade priorities, using only baseline simulation inputs. We also conducted a benchmark in which the agent identified the setup and proposed improvements from a suite of natural language prompts, with some supplied with a relevant physics research paper, of varying high energy physics (HEP) problem settings. This work establishes experimental design as a constrained search problem under physical law and introduces a new benchmark for autonomous, simulation-driven scientific reasoning in complex instruments.