# AI Agents Can Already Autonomously Perform Experimental High Energy Physics

arXiv: https://arxiv.org/abs/2603.20179 · HTML: https://mlsanity.com/paper/2603.20179/

## Key facts

- Cited by 10 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 13 of its 85 references that are in the map.
- First posted on arXiv 20 Mar 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, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [Automating High Energy Physics Data Analysis with LLM-Powered Agents](https://mlsanity.com/paper/2512.07785/) (2025)
- [Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics](https://mlsanity.com/paper/2404.08001/) (2024)
- [GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation](https://mlsanity.com/paper/2602.15039/) (2026)
- [An End-to-end Architecture for Collider Physics and Beyond](https://mlsanity.com/paper/2603.14553/) (2026)
- [Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data](https://mlsanity.com/paper/2603.05735/) (2026)
- [Agents of Discovery](https://mlsanity.com/paper/2509.08535/) (2025)
- [Pixi: Unified Software Development and Distribution for Robotics and AI](https://mlsanity.com/paper/2511.04827/) (2025)
- [CelloAI Benchmarks: Toward Repeatable Evaluation of AI Assistants](https://mlsanity.com/paper/2603.01051/) (2026)

## Built on by (most cited first, 10 of 10)

- [Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction](https://mlsanity.com/paper/2605.13950/) (2026)
- [El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation](https://mlsanity.com/paper/2604.14609/) (2026)
- [Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments](https://mlsanity.com/paper/2607.25145/) (2026)
- [Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows](https://mlsanity.com/paper/2604.25345/) (2026)
- [Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis](https://mlsanity.com/paper/2606.10381/) (2026)
- [Experiments in Agentic AI for Science](https://mlsanity.com/paper/2605.26305/) (2026)
- [Agentic AI for Gravitational Wave Data Analysis: A Head-to-Head Comparison of Coding Agents Executing a Matched Filter Pipeline on Einstein Telescope Simulated Data](https://mlsanity.com/paper/2605.28916/) (2026)
- [AgentRivet: an automated system for producing Rivet routines from journal publications](https://mlsanity.com/paper/2606.13535/) (2026)
- [Machine learning for the LHC physics program: a 2025-2026 stocktake](https://mlsanity.com/paper/2609.32874/) (2026)
- [Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery](https://mlsanity.com/paper/2610.12293/) (2026)

## Abstract (arXiv)

Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipeline with minimal expert-curated input. Given access to a HEP dataset, an execution framework, and a corpus of prior experimental literature, we find that Claude Code succeeds in automating all stages of a typical analysis: event selection, background estimation, uncertainty quantification, statistical inference, and paper drafting. We argue that the experimental HEP community is underestimating the current capabilities of these systems, and that most proposed agentic workflows are too narrowly scoped or scaffolded to specific analysis structures. We present a proof-of-concept framework, Just Furnish Context (JFC), that integrates autonomous analysis agents with literature-based knowledge retrieval and multi-agent review, and show that this is sufficient to plan, execute, and document a credible high energy physics analysis. We demonstrate this by conducting analyses on open data from ALEPH, DELPHI, and CMS to perform electroweak, QCD, and Higgs boson measurements. We present two of those results in a condensed short paper form -- a CMS Run1 Open Data H→ τ^+τ^- to demonstrate performance on a well-established result, and the first Lund plane measurement on LEP data -- a genuinely novel result and, to our knowledge, the first produced autonomously by an AI agent. Rather than replacing physicists, these tools promise to offload the repetitive technical burden of analysis code development, freeing researchers to focus on physics insight, truly novel method development, and rigorous validation. Given these developments, we advocate for new strategies for how the community trains students, organizes analysis efforts, and allocates human expertise.