# Towards Agentic AI on Particle Accelerators

arXiv: https://arxiv.org/abs/2409.06336 · HTML: https://mlsanity.com/paper/2409.06336/

## Key facts

- Cited by 5 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 19 of its 34 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## 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, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Empowering Working Memory for Large Language Model Agents](https://mlsanity.com/paper/2312.17259/) (2023)
- [CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks](https://mlsanity.com/paper/2406.02524/) (2024)
- [Causal Agent based on Large Language Model](https://mlsanity.com/paper/2408.06849/) (2024)
- [GAIA: A General AI Assistant for Intelligent Accelerator Operations](https://mlsanity.com/paper/2405.01359/) (2024)
- [Towards Unlocking Insights from Logbooks Using AI](https://mlsanity.com/paper/2406.12881/) (2024)
- [Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program](https://mlsanity.com/paper/2408.08676/) (2024)

## Built on by (most cited first, 5 of 5)

- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops](https://mlsanity.com/paper/2412.17149/) (2024)
- [Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator](https://mlsanity.com/paper/2509.17255/) (2025)
- [Agentic System with Modal Logic for Autonomous Diagnostics](https://mlsanity.com/paper/2509.11943/) (2025)
- [A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility](https://mlsanity.com/paper/2607.24663/) (2026)

## Abstract (arXiv)

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show three examples, where we demonstrate the viability of such architecture.