mlsanityData to 7 Oct 2026

Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data

arXiv 2603.05735 ↗First posted 5 Mar 2026hep-ex cs.AI hep-phcited by 4

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

We present an AI agentic measurement of the thrust distribution in e+e- collisions at √s=91.2~GeV using archived ALEPH data. The analysis and all note writing is carried out entirely by AI agents (OpenAI Codex and Anthropic Claude) under expert physicist direction. A fully corrected spectrum is obtained via Iterative Bayesian Unfolding and Monte Carlo based corrections. This work represents a step toward a theory-experiment loop in which AI agents assist with experimental measurements and theoretical calculations, and synthesize insights by comparing the results, thereby accelerating the cycle that drives discovery in fundamental physics. Our work suggests that precision physics, leveraging the open LEP data and advanced theoretical landscape, provides an ideal testing ground for developing advanced AI systems for scientific applications.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 6 of its 45 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

6 of 45 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery7 Oct

Other references · 5

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  4. 2025Early science acceleration experiments with GPT-5cited by 35
  5. 2026Accelerating Scientific Research with Gemini: Case Studies and Common Techniquescited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026AI Agents Can Already Autonomously Perform Experimental High Energy Physicscited by 10
  2. 2026An End-to-end Architecture for Collider Physics and Beyondcited by 5
  3. 2026Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthroughcited by 1
  4. 2026AgentRivet: an automated system for producing Rivet routines from journal publicationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
  2. 2025Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator
  3. 2026GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation
  4. 2025PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
  5. 2026PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
  6. 2026From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard Model
  7. 2026Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
  8. 2025Can Theoretical Physics Research Benefit from Language Agents?