We present an agentic measurement of the thrust distribution in \(e^+e^-\) collisions at \(\sqrt{s}=91.2\) GeV using ALEPH archived data. This work was carried out through an AI agent–physicist collaboration, using interactive natural-language prompting of Anthropic Claude and OpenAI Codex. Under physicist guidance, the agents wrote and executed all analysis code and drafted the majority of the text included in this paper. A fully-corrected thrust spectrum is obtained via Iterative Bayesian Unfolding and Monte Carlo based corrections. The principal contribution of this work is the demonstration of the agentic analysis, with thrust serving as a benchmark observable for the method. Dedicated precision measurements of thrust are reported in the community elsewhere. 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 AI agent systems for scientific applications.
- Open Access
- Article
Agentic AI—Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data
- Anthony Badea 1,*,
- Marcello Maggi 2,
- Christopher McGinn 3,
- Austin Baty 4,
- Yi Chen 5,
- Hannah Bossi 3,
- Gian Michele Innocenti 3,
- Jingyu Zhang 5,
- Yu-Chen Chen 3,
- Tzu-An Sheng 3,
- Yen-Jie Lee 3,
- The Electron-Positron Alliance †
Author Information
Received: 12 Jun 2026 | Revised: 17 Sep 2026 | Accepted: 28 Sep 2026 | Published: 30 Sep 2026
Abstract
References
- 1.
The Electron-Positron Alliance. Available online: https://ee-alliance.org/home/ (accessed on 18 February 2026).
- 2.
Badea, A.; Baty, A.; Chang, P.; et al. Measurements of Two-Particle Correlations in e+e− Collisions at 91 GeV with ALEPH Archived Data. Phys. Rev. Lett. 2019, 123, 212002. https://doi.org/10.1103/physrevlett.123.212002.
- 3.
Chen, Y.; Badea, A.; Baty, A.; et al. Jet energy spectrum and substructure in e+e− collisions at 91.2 GeV with ALEPH Archived Data. J. High Energy Phys. 2022, 2022, 8. https://doi.org/10.1007/jhep06(2022)008.
- 4.
Chen, Y.C.; Chen, Y.; Badea, A.; et al. Long-range near-side correlation in e+e− collisions at 183–209 GeV with ALEPH archived data. Phys. Lett. B 2024, 856, 138957. https://doi.org/10.1016/j.physletb.2024.138957.
- 5.
Bossi, H.; Chen, Y.; Chen, Y.C.; et al. Energy Correlators from Partons to Hadrons: Unveiling the Dynamics of the Strong Interactions with Archival ALEPH Data. arXiv 2025, arXiv:2511.00149.
- 6.
Badea, A.; Baty, A.; Bossi, H.; et al. Unbinned measurement of thrust in e+e− collisions at √s = 91.2 GeV with ALEPH archived data. arXiv 2025, arXiv:2510.22038.
- 7.
Anthropic. Accelerating Scientific Research. Available online: https://www.anthropic.com/news/accelerating-scientific-research (accessed on 15 January 2026).
- 8.
OpenAI. Advancing Science and Math with GPT-5.2. Available online: https://openai.com/index/gpt-5-2-for-science-and-math/ (accessed on 11 December 2025).
- 9.
Google DeepMind. Gemini Deep Think: Accelerating Mathematical and Scientific Discovery. Available online: https://deepmind.google/blog/accelerating-mathematical-and-scientific-discovery-with-gemini-deep-think/ (accessed on 11 February 2026).
- 10.
OpenAI. GPT-5.2 Derives a New Result in Theoretical Physics. Available online: https://openai.com/index/new-result-theoretical-physics/ (accessed on 13 February 2026).
- 11.
Google DeepMind. AlphaProteo: Generating Novel Proteins for Biology and Health Research. Available online: https://deepmind.google/blog/alphaproteo-generates-novel-proteins-for-biology-and-health-research/ (accessed on 13 February 2026).
- 12.
ALEPH Collaboration. Studies of QCD at e+e− centre-of-mass energies between 91 and 209 GeV. Eur. Phys. J. C 2004, 35, 457–486. https://doi.org/10.1140/epjc/s2004-01891-4.
- 13.
ALEPH Documentation. Available online: https://aleph-new.docs.cern.ch (accessed on 16 September 2026).
- 14.
Brown, T.; Mann, B.; Ryder, N.; et al. Language Models are Few-Shot Learners. In Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Virtual Event, 6–12 December 2020; vol. 33, pp. 1877–1901.
- 15.
Wei, J.; Wang, X.; Schuurmans, D.; et al. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, LA, USA, 28 November–9 December 2022; vol. 35, pp. 24824–24837.
- 16.
Abolhasani, M.; Kumacheva, E. The rise of self-driving labs in chemical and materials sciences. Nat. Synth. 2023, 2, 483–492. https://doi.org/10.1038/s44160-022-00231-0.
- 17.
MacLeod, B.P.; Parlane, F.G.L.; Morrissey, T.D.; et al. Self-driving laboratory for accelerated discovery of thin-film materials. Sci. Adv. 2020, 6, eaaz8867. https://doi.org/10.1126/sciadv.aaz8867.
- 18.
Chen, Z.; Chen, S.; Ning, Y.; et al. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery. arXiv 2024, arXiv:2410.05080.
- 19.
Lu, C.J.J.; Lu, C.; Lange, R.T.; et al. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery. arXiv 2024, arXiv:2408.06292.
- 20.
Woodruff, D.P.; Cohen-Addad, V.; Jain, L.; et al. Accelerating Scientific Research with Gemini: Case Studies and Common Techniques. arXiv 2026, arXiv:2602.03837.
- 21.
Bubeck, S.; Coester, C.; Eldan, R.; et al. Early science acceleration experiments with GPT-5. arXiv 2025, arXiv:2511.16072.
- 22.
Guevara, A.; Lupsasca, A.; Skinner, D.B.; et al. Single-minus gluon tree amplitudes are nonzero. arXiv 2026, arXiv:2602.12176.
- 23.
Schwartz, M.D. Resummation of the C-Parameter Sudakov Shoulder Using Effective Field Theory. arXiv 2026, arXiv:2601.02484.
- 24.
Wang, H.; Fu, T.; Du, Y.; et al. Scientific discovery in the age of artificial intelligence. Nature 2023, 620, 47–60. https://doi.org/10.1038/s41586-023-06221-2. Correction in: Nature 2023, 621, E33. https://doi.org/10.1038/s41586-023-06559-7.
- 25.
Messeri, L.; Crockett, M.J. Artificial intelligence and illusions of understanding in scientific research. Nature 2024, 627, 49–58. https://doi.org/10.1038/s41586-024-07146-0.
- 26.
Farhi, E. Quantum Chromodynamics Test for Jets. Phys. Rev. Lett. 1977, 39, 1587–1588. https://doi.org/10.1103/physrevlett.39.1587.
- 27.
Abbate, R.; Fickinger, M.; Hoang, A.H.; et al. Thrust at N3LL with Power Corrections and a Precision Global Fit for αs(mZ). Phys. Rev. D 2011, 83, 074021. https://doi.org/10.1103/physrevd.83.074021.
- 28.
Benitez, M.A.; Hoang, A.H.; Mateu, V.; et al. On Determining αs(mZ) from Dijets in e+e− Thrust. arXiv 2024, arXiv:2412.15164.
- 29.
Particle Data Group; Workman, R.L.; Burkert, V.D.; et al. Review of Particle Physics. Prog. Theor. Exp. Phys. 2022, 2022, 083C01. https://doi.org/10.1093/ptep/ptac097.
- 30.
Decamp, D.; Deschizeaux, B.; Lees, J.P.; et al. ALEPH: A detector for electron-positron annihilations at LEP. Nucl. Instrum. Methods Phys. Res. A 1990, 294, 121–178. https://doi.org/10.1016/0168-9002(90)91831-u.
- 31.
ALEPH Collaboration; Buskulic, D.; Casper, D.; et al. Performance of the ALEPH detector at LEP. Nucl. Instrum. Methods Phys. Res. A 1995, 360, 481–506. https://doi.org/10.1016/0168-9002(95)00138-7.
- 32.
ALEPH Collaboration; Barate, R.; Buskulic, D.; et al. Studies of quantum chromodynamics with the ALEPH detector. Phys. Rep. 1998, 294, 1–165. https://doi.org/10.1016/s0370-1573(97)00045-8.
- 33.
Sjöstrand, T.; Edén, P.; Friberg, C.; et al. High-energy-physics event generation with Pythia 6.1. Comput. Phys. Commun. 2001, 135, 238–259. https://doi.org/10.1016/s0010-4655(00)00236-8.
- 34.
Brandt, S.; Dahmen, H.D. Axes and Scalar Measures of Two-Jet and Three-Jet Events. Z. Phys. C 1979, 1, 61–70. https://doi.org/10.1007/bf01450381.
- 35.
Bähr, M.; Gieseke, S.; Gigg, M.A.; et al. Herwig++ physics and manual. Eur. Phys. J. C 2008, 58, 639–707. https://doi.org/10.1140/epjc/s10052-008-0798-9.
- 36.
Buckley, A.; Butterworth, J.; Grellscheid, D.; et al. Rivet user manual. Comput. Phys. Commun. 2013, 184, 2803–2819. https://doi.org/10.1016/j.cpc.2013.05.021.
- 37.
Buckley, A. Thrust.hh Source File. RIVET Hep Forge 2011. Available online: https://rivet.hepforge.org/code/1.7.0/a00541_source.html (accessed on 25 February 2023).
- 38.
Belle II Collaboration. Belle II Software: Thrust Class. Available online: https://software.belle2.org/prerelease-10-00-00a/doxygen/classBelle2_1_1Thrust.html#a82233fb167d2bdefb9b3b9e2450c30a9 (accessed on 14 July 2025).
- 39.
D’Agostini, G. A Multidimensional unfolding method based on Bayes’ theorem. Nucl. Instrum. Methods Phys. Res. A 1995, 362, 487–498. https://doi.org/10.1016/0168-9002(95)00274-x.
- 40.
D’Agostini, G. Improved iterative Bayesian unfolding. arXiv 2010, arXiv:1010.0632.
- 41.
Adye, T. Unfolding algorithms and tests using RooUnfold. In Proceedings of the PHYSTAT 2011 Workshop on Statistical Issues Related to Discovery Claims in Search Experiments and Unfolding, Geneva, Switzerland, 17–20 January 2011; pp. 313–318.
- 42.
Bierlich, C.; Chakraborty, S.; Desai, N.; et al. A comprehensive guide to the physics and usage of PYTHIA 8.3. SciPost Phys. Codebases 2022, 8. https://doi.org/10.21468/scipostphyscodeb.8.
- 43.
Jadach, S.; Ward, B.F.L.; Wąs, Z.; et al. Multi-photon Monte Carlo event generator KKMCee for lepton and quark pair production in lepton colliders. Comput. Phys. Commun. 2023, 283, 108556. https://doi.org/10.1016/j.cpc.2022.108556.
- 44.
Bellm, J.; Gieseke, S.; Grellscheid, D.; et al. Herwig 7.0/Herwig++ 3.0 release note. Eur. Phys. J. C 2016, 76, 196. https://doi.org/10.1140/epjc/s10052-016-4018-8.
- 45.
Bellm, J.; Gieseke, S.; Grellscheid, D.; et al. Herwig 7.1 Release Note. arXiv 2017, arXiv:1705.06919.
- 46.
Bewick, G.; Ferrario Ravasio, S.; Gieseke, S.; et al. Herwig 7.3 Release Note. Eur. Phys. J. C 2024, 84, 1053. https://doi.org/10.1140/epjc/s10052-024-13211-9.
- 47.
Bothmann, E.; Singh Chahal, G.; Höche, S.; et al. Event generation with Sherpa 2.2. SciPost Phys. 2019, 7, 034. https://doi.org/10.21468/scipostphys.7.3.034.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com