- Physical Review Journals
All JournalsPhysics Magazine

PRX Intelligence

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

lara-hpc: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling

William Dawson1, Louis Beal2, Yoann Curé3, Giuseppe Fisicaro4,*, Dorian Rolland3, and Luigi Genovese3

  • *Contact author: giuseppe.fisicaro@cnr.it
PDF

PRX Intelligence 1, 025001 – Published 10 November, 2026

DOI: https://doi.org/10.1103/cp6v-t93q

Abstract

Large language models and agentic systems have recently demonstrated potential for automating scientific workflows, including atomistic simulations. However, their deployment in high-performance computing (HPC) environments remains limited by the lack of mechanisms ensuring correctness, reproducibility, and safe interaction with computational resources. Generated workflows suffer from inconsistencies, incorrect application programming interface usage, or invalid physical configurations—leading to failed or unreliable simulations. In this work, we introduce lara-hpc (Lara Agentic Research Assistant for HPC), a validation-driven agentic framework to enable reliable workflow generation for atomistic modeling on HPC systems. Our approach is based on three key components: (1) a controlled execution layer that mediates all interactions with HPC resources; (2) simulation-native validation through dry-run capabilities, enabling execution-level verification without incurring resource cost; and (3) a multiphase agentic pipeline combining retrieval-augmented generation and iterative refinement. We demonstrate the effectiveness of this approach by performing an end-to-end atomistic simulation workflow on HPC by applying lara-hpc to density functional theory simulations. The results show that validation-driven generation significantly improves robustness and enables iterative correction of both syntactic and physical inconsistencies. More broadly, this work advocates for a shift from generation-first to validation-first paradigms in artificial-intelligence-assisted scientific computing. We argue that the future task of the computational physics community is to develop domain-specific agentic systems based on structured tooling to realize an HPC enabled copiloted research ecosystem.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (44)

  1. M. Chen et al., Evaluating large language models trained on code, arXiv:2107.03374.
  2. J. Gottweis et al., Towards an AI co-scientist, Nature (London) 655, 487 (2026).
  3. Y. Zimmermann et al., 32 examples of LLM applications in materials science and chemistry: Towards automation, assistants, agents, and accelerated scientific discovery, Mach. Learn.: Sci. Technol. 6, 030701 (2025).
  4. Y. Zimmermann et al., Reflections from the 2024 large language model (LLM) hackathon for applications in materials science and chemistry, arXiv:2411.15221.
  5. N. Alampara, A. Aneesh, M. Ríos-García, A. Mirza, M. Schilling-Wilhelmi, A. A. Aghajani, M. Sun, G. Prastalo, and K. M. Jablonka, General-purpose models for the chemical sciences: LLMs and beyond, Chem. Rev. 126, 2484 (2026).
  6. I. Mandal, J. Soni, M. Zaki, M. M. Smedskjaer, K. Wondraczek, L. Wondraczek, N. N. Gosvami, and N. M. Anoop Krishnan, Evaluating large language model agents for automation of atomic force microscopy, Nat. Commun. 16, 9104 (2025).
  7. A. M. Bran, S. Cox, O. Schilter, C. Baldassari, A. D. White, and P. Schwaller, Augmenting large language models with chemistry tools, Nat. Mach. Intell. 6, 525 (2024).
  8. A. Vriza, U. Kornu, A. Koneru, H. Chan, and S. K. R. S. Sankaranarayanan, Multi-agentic AI framework for end-to-end atomistic simulations, Digit. Discov. 5, 440 (2026).
  9. C. Lu, C. Lu, R. T. Lange, Y. Yamada, S. Hu, J. Foerster, D. Ha, and J. Clune, Towards end-to-end automation of AI research, Nature (London) 651, 914 (2026).
  10. S. Gao et al., Democratizing AI scientists using tooluniverse, arXiv:2509.23426.
  11. Y. Qu, K. Huang, M. Yin, K. Zhan, D. Liu, D. Yin, H. C. Cousins, W. A. Johnson, X. Wang, M. Shah, R. B. Altman, D. Zhou, M. Wang, and L. Cong, CRISPR-GPT for agentic automation of gene-editing experiments, Nat. Biomed. Eng. 10, 245 (2026).
  12. Y. Zou, A. H. Cheng, A. Aldossary, J. Bai, S. X. Leong, J. A. Campos-Gonzalez-Angulo, C. Choi, C. T. Ser, G. Tom, A. Wang, Z. Zhang, I. Yakavets, H. Hao, C. Crebolder, V. Bernales, and A. Aspuru-Guzik, El Agente: An autonomous agent for quantum chemistry, Matter 8, 102263 (2025).
  13. T. D. Pham, A. Tanikanti, and M. Keçeli, Chemgraph as an agentic framework for computational chemistry workflows, Commun. Chem. 9, 33 (2026).
  14. Q. Campbell, S. Cox, J. Medina, B. Watterson, and A. D. White, MDCrow: Automating molecular dynamics workflows with large language models, Mach. Learn.: Sci. Technol. 7, 025037 (2026).
  15. Z. Wang, H. Huang, H. Zhao, C. Xu, S. Zhu, J. Janssen, and V. Viswanathan, Dreams: Density functional theory based research engine for agentic materials simulation, arXiv:2507.14267.
  16. E. Deelman, D. Gannon, M. Shields, and I. Taylor, Workflows and e-Science: An overview of workflow system features and capabilities, Future Gener. Comput. Syst. 25, 528 (2009).
  17. S. P. Huber et al., Aiida 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance, Sci. Data 7, 300 (2020).
  18. R. M. Martin, Electronic Structure: Basic Theory and Practical Methods (Cambridge University Press, Cambridge, UK, 2020).
  19. V. Brázdová and D. R. Bowler, Atomistic Computer Simulations: A Practical Guide (Wiley-VCH, Weinheim, Germany, 2013).
  20. P. Lewis et al., Retrieval-augmented generation for knowledge-intensive NLP tasks, in Advances in Neural Information Processing Systems, edited by H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Curran Associates, Inc., Red Hook, NY, 2020), Vol. 33, pp. 9459–9474.
  21. S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, ReAct: Synergizing reasoning and acting in language models, in Proceedings of the Eleventh International Conference on Learning Representations (ICLR, 2023), pp. 30084–30116.
  22. L. E. Ratcliff, W. Dawson, G. Fisicaro, D. Caliste, S. Mohr, A. Degomme, B. Videau, V. Cristiglio, M. Stella, M. D'Alessandro, S. Goedecker, T. Nakajima, T. Deutsch, and L. Genovese, Flexibilities of wavelets as a computational basis set for large-scale electronic structure calculations, J. Chem. Phys. 152, 194110 (2020).
  23. W. Dawson, L. Beal, L. E. Ratcliff, M. Stella, T. Nakajima, and L. Genovese, Exploratory data science on supercomputers for quantum mechanical calculations, Electron. Struct. 6, 027003 (2024).
  24. A. Blount, A. Gulli, S. Saboo, M. Zimmermann, and V. Vuskovic, Introduction to agents, kaggle/Google Whitepaper, 2025, https://www.kaggle.com/whitepaper-introduction-to-agents, accessed: 11 April 2026.
  25. L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang, Z. Chen, J. Tang, X. Chen, Y. Lin, W. X. Zhao, Z. Wei, and J. Wen, A survey on large language model based autonomous agents, Front. Comput. Sci. 18, 186345 (2024).
  26. Y. Gan et al., Navigating the risks: A survey of security, privacy, and ethics threats in LLM-based agents, arXiv:2411.09523.
  27. OpenAI, A practical guide to building agents, OpenAI Documentation, 2024, https://platform.openai.com/docs/guides/agents, accessed: 11 April 2026.
  28. C. Packer et al., MemGPT: Towards LLMs as operating systems, arXiv:2310.08560.
  29. W. Xu, Z. Liang, K. Mei, H. Gao, J. Tan, and Y. Zhang, A-MEM: Agentic memory for LLM agents, in Advances in Neural Information Processing Systems, edited by D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, and N. Chen (Curran Associates, Inc., Red Hook, NY, 2025), Vol. 38, pp. 17577–17604.
  30. A. Singh, A. Ehtesham, S. Kumar, and T. T. Khoei, Agentic retrieval-augmented generation: A survey on agentic RAG, arXiv:2501.09136.
  31. A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y. Yang, S. Gupta, B. P. Majumder, K. Hermann, S. Welleck, A. Yazdanbakhsh, and P. Clark, Self-refine: Iterative refinement with self-feedback, in Advances in Neural Information Processing Systems, edited by A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Curran Associates, Inc., Red Hook, NY, 2023), Vol. 36, pp. 46534–46594.
  32. BigDFT developers, RemoteManager repository, canonical maintained project page, 2026, https://gitlab.com/l_sim/remotemanager, accessed: 16 September 2026.
  33. BigDFT developers, lara-hpc: Lara agentic research assistant for HPC, canonical maintained project page, 2026, http://github.com/bigdft-group/lara-hpc, accessed: 16 September 2026.
  34. G. Comanici et al., Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities, arXiv:2507.06261.
  35. G. Fisicaro, S. Filice, S. Scalese, G. Compagnini, R. Reitano, L. Genovese, S. Goedecker, I. Deretzis, and A. La Magna, Wet environment effects for ethanol and water adsorption on anatase TiO2 (101) surfaces, J. Phys. Chem. C 124, 2406 (2020).
  36. P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing, ACM Comput. Surv. 55, 1 (2023).
  37. Y. Weng, M. Zhu, Q. Xie, Q. Sun, Z. Lin, S. Liu, and Y. Zhang, DeepScientist: Advancing frontier-pushing scientific findings progressively, in Fourteenth International Conference on Learning Representations, edited by C. Vondrick, B. Hariharan, C. Raffel, L. Pinto, D. Yang, and A. Faust (ICLR, 2026), Vol. 2026, pp. 47981–48037.
  38. Analemma Intelligence, FARS: Fully Automated Research System, 2026, https://analemma.ai/blog/introducing-fars/, accessed: 9 April 2026.
  39. Y. Lyu et al., EvoScientist: Towards multi-agent evolving AI scientists for end-to-end scientific discovery, arXiv:2603.08127.
  40. Y. Li, X. Yang, X. Yang, X. Wang, W. Liu, and J. Bian, R&D-Agent-Quant: A multi-agent framework for data-centric factors and model joint optimization, in Advances in Neural Information Processing Systems, edited by D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, and N. Chen (Curran Associates, Inc., Red Hook, NY, 2025), Vol. 38.
  41. S. Schmidgall, Y. Su, Z. Wang, X. Sun, J. Wu, X. Yu, J. Liu, M. Moor, and Z. Liu, Agent laboratory: Using LLM agents as research assistants, Findings of the Association for Computational Linguistics: EMNLP 2025, edited by C. Christodoulopoulos, T. Chakraborty, C. Rose, and V. Peng (Association for Computational Linguistics, 2025), pp. 5977–6043.
  42. F. Villaescusa-Navarro et al., Denario Project: Deep Knowledge Artificial Intelligence Agents for Scientific Discovery, PRX Intelligence 1, 021001 (2026).
  43. T. Kwa et al., Measuring AI ability to complete long tasks, METR Blog, 2025, https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/, accessed: 11 April 2026.
  44. R. Raj, H. Wang, and T. Krishna, A CPU-centric perspective on agentic AI, arXiv:2511.00739.

Outline

Information

PRX Intelligence 1, 025001– Published 10 November, 2026
  • Received 29 April 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation