pith. sign in

arxiv: 2606.09422 · v1 · pith:GLTG4JYMnew · submitted 2026-06-08 · ❄️ cond-mat.mtrl-sci

A Robust Agentic Framework for Expert-Level Automation of Atomistic Simulations

Yutack Park , Yeonwoo Chung , Jinmu You , Jisu Kim , Suyeon Ju , Seungwu Han This is my paper

Pith reviewed 2026-06-27 15:38 UTC · model grok-4.3

classification ❄️ cond-mat.mtrl-sci
keywords agentic frameworkatomistic simulationssilent errorsmachine learning interatomic potentialsliquid electrolyteautomationmaterials optimization
0
0 comments X

The pith

Paimon suppresses silent errors in agentic workflows for atomistic simulations to boost reliability.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents Paimon as a platform that automates the human-intensive steps in atomistic simulations, such as input preparation and data analysis, after machine learning interatomic potentials removed earlier computational limits. It focuses on making agentic workflows more dependable by addressing silent errors, which are outputs that look reasonable but violate physical principles. Hundreds of trials on an expert-level liquid electrolyte simulation task provide the main evidence for this improvement. The framework also shows it can collaborate with external agents and recreate methods described in published papers, supporting an end-to-end automated process.

Core claim

Paimon is introduced as a Platform for Agentic Integration in Materials Optimization and Nanoscale-simulations that serves as an agent harness. Testing across hundreds of trials on liquid electrolyte simulations demonstrates that it substantially improves the reliability of agentic workflows by suppressing silent errors. The system further enables cooperation with external scientific agents and autonomous reproduction of simulation methodologies from the literature, allowing a continuous, science-centric workflow across the full simulation lifecycle.

What carries the argument

Paimon, a Platform for Agentic Integration in Materials Optimization and Nanoscale-simulations, which functions as an agent harness to suppress silent errors in automated simulation workflows.

If this is right

  • Researchers gain a continuous workflow that keeps focus on scientific questions rather than mechanical tasks.
  • Agentic systems become capable of reproducing published simulation methodologies without direct human scripting.
  • Integration with external scientific agents extends the reach of individual automation setups.
  • Silent errors decrease in frequency, reducing the chance that incorrect but believable outputs enter research pipelines.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Success here could encourage similar robustness layers in agent frameworks for other computational chemistry or physics domains.
  • If the suppression of silent errors generalizes, post-processing checks might become less necessary for routine tasks.
  • The approach might shorten the overall time from idea to validated result in materials research by removing repeated human interventions.

Load-bearing premise

Agentic workflows can be made robust enough to suppress silent errors across diverse simulation tasks without domain-specific human tuning or post-hoc validation.

What would settle it

A new simulation task outside liquid electrolytes where Paimon still generates plausible but physically incorrect results in repeated trials.

read the original abstract

Traditionally, atomistic simulation has been constrained by the computational scaling limits of ab initio methods and the parameterization overhead of empirical force fields. The recent emergence of universal machine learning interatomic potentials has significantly mitigated these bottlenecks, offering near-quantum accuracy and generalizability across diverse chemical spaces at a fraction of the computational cost. However, this shift has relocated the bottleneck to the human dimension: time-consuming mechanical processes, such as input preparation and data analysis, now dominate the research lifecycle. We introduce Paimon, a Platform for Agentic Integration in Materials Optimization and Nanoscale-simulations. Through hundreds of trials on an expert-level liquid electrolyte simulation, we show that Paimon substantially improves the reliability of agentic workflows by suppressing silent errors: plausible yet physically incorrect results. We further demonstrate that Paimon can cooperate with an external scientific agent and autonomously reproduce simulation methodologies from the literature. As an agent harness for atomistic simulations, Paimon affords researchers a continuous, science-centric workflow throughout the entire simulation lifecycle.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript introduces Paimon, a Platform for Agentic Integration in Materials Optimization and Nanoscale-simulations. It claims that, through hundreds of trials on an expert-level liquid electrolyte simulation, Paimon substantially improves the reliability of agentic workflows by suppressing silent errors (plausible yet physically incorrect results). It further claims that Paimon can cooperate with an external scientific agent to autonomously reproduce simulation methodologies from the literature, providing a continuous, science-centric workflow for atomistic simulations.

Significance. If the empirical demonstration holds with rigorous quantitative support, the work could meaningfully address the human-time bottleneck in atomistic simulations by enabling more reliable automation. The approach leverages recent universal machine learning interatomic potentials and positions itself as an agent harness, which aligns with growing interest in AI-assisted scientific workflows. However, the absence of metrics, baselines, error definitions, or data details in the provided text prevents a concrete assessment of impact or reproducibility.

major comments (1)
  1. [Abstract] Abstract: the central claim that Paimon 'substantially improves the reliability of agentic workflows by suppressing silent errors' through 'hundreds of trials' supplies no metrics, baselines, definitions of silent errors or physically incorrect results, or data details, so the empirical assertion cannot be evaluated.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive review. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that Paimon 'substantially improves the reliability of agentic workflows by suppressing silent errors' through 'hundreds of trials' supplies no metrics, baselines, definitions of silent errors or physically incorrect results, or data details, so the empirical assertion cannot be evaluated.

    Authors: We agree that the abstract as written does not supply the requested quantitative elements and therefore cannot be evaluated on its own. The body of the manuscript contains the experimental details, but these are not summarized or defined in the abstract. In the revised manuscript we will expand the abstract to include explicit metrics (e.g., success-rate improvement across the trial set), a concise definition of silent errors, the baselines employed, and a pointer to the data repository. This change will be made while preserving the abstract's length and focus. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper presents an empirical demonstration of an agentic framework (Paimon) through hundreds of trials on liquid electrolyte simulations, claiming improved reliability via suppression of silent errors. No equations, fitted parameters, derivations, or self-referential definitions appear in the provided text. The central claim rests on external trial outcomes rather than any reduction to inputs by construction, self-citation chains, or renamed known results. This is a standard non-circular empirical report; the derivation chain is absent and the argument is self-contained against the described benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review yields no information on free parameters, axioms, or invented entities used in the work.

pith-pipeline@v0.9.1-grok · 5719 in / 1042 out tokens · 20298 ms · 2026-06-27T15:38:27.439856+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

82 extracted references · 7 linked inside Pith

  1. [1]

    Cohen, A.J., Mori-S´ anchez, P., Yang, W.: Chal- lenges for density functional theory. Chem. Rev. 112(1), 289–320 (2012)

    2012

  2. [2]

    Academic Press, Amsterdam (2023)

    Frenkel, D., Smit, B.: Understanding Molecular Simulation: From Algorithms to Applications, 3rd edn. Academic Press, Amsterdam (2023)

    2023

  3. [3]

    Zhang, Y.-W., Sorkin, V., Aitken, Z.H., Politano, A., Behler, J., Thompson, A.P., Ko, T.W., Ong, S.P., Chalykh, O., Korogod, D., Podryabinkin, E., Shapeev, A., Li, J., Mishin, Y., Pei, Z., Liu, X., Kim, J., Park, Y., Hwang, S., Han, S., Sheriff, K., Cao, Y., Freitas, R.: Roadmap for the develop- ment of machine learning-based interatomic poten- tials. Mod...

    2025

  4. [4]

    Chen, C., Ong, S.P.: A universal graph deep learn- ing interatomic potential for the periodic table. Nat. Comput. Sci.2(11), 718–728 (2022)

    2022

  5. [5]

    Deng, B., Zhong, P., Jun, K., Riebesell, J., Han, K., Bartel, C.J., Ceder, G.: CHGNet as a pretrained universal neural network potential for charge- informed atomistic modelling. Nat. Mach. Intell. 5(9), 1031–1041 (2023)

    2023

  6. [6]

    Batatia, I., Benner, P., Chiang, Y., Elena, A.M., Kov´ acs, D.P., Riebesell, J., Advincula, X.R., Asta, M., Avaylon, M., Baldwin, W.J., Berger, F., Bern- stein, N., Bhowmik, A., Bigi, F., Blau, S.M., C˘ arare, 13 V., Ceriotti, M., Chong, S., Darby, J.P., De, S., Pia, F.D., Deringer, V.L., Elijoˇ sius, R., El-Machachi, Z., Falcioni, F., Fako, E., Ferrari, ...

    2025

  7. [7]

    Park, Y., Kim, J., Hwang, S., Han, S.: Scalable par- allel algorithm for graph neural network interatomic potentials in molecular dynamics simulations. J. Chem. Theory Comput.20(11), 4857–4868 (2024)

    2024

  8. [8]

    Kim, J., You, J., Park, Y., Lim, Y., Kang, Y., Kim, J., Jeon, H., Ju, S., Hong, D., Lee, S.Y., Choi, S., Kim, Y., Lee, J.W., Han, S.: Optimizing cross-domain transfer for universal machine learn- ing interatomic potentials. Nat. Commun.17, 3432 (2026)

    2026

  9. [9]

    Curtarolo, S., Setyawan, W., Hart, G.L.W., Jahn´ atek, M., Chepulskii, R.V., Taylor, R.H., Wang, S., Xue, J., Yang, K., Levy, O., Mehl, M.J., Stokes, H.T., Demchenko, D.O., Morgan, D.: AFLOW: an automatic framework for high- throughput materials discovery. Comput. Mater. Sci.58, 218–226 (2012)

    2012

  10. [10]

    Huber, S.P., Zoupanos, S., Uhrin, M., Talirz, L., Kahle, L., H¨ auselmann, R., Gresch, D., M¨ uller, T., Yakutovich, A.V., Andersen, C.W., Ramirez, F.F., Adorf, C.S., Gargiulo, F., Kumbhar, S., Passaro, E., Johnston, C., Merkys, A., Cepellotti, A., Mounet, N., Marzari, N., Kozinsky, B., Pizzi, G.: AiiDA 1.0, a scalable computational infrastructure for aut...

    2020

  11. [11]

    Youn, Y., Lee, M., Hong, C., Kim, D., Kim, S., Jung, J., Yim, K., Han, S.: AMP2: a fully automated program for ab initio calculations of crystalline materials. Comput. Phys. Commun.256, 107450 (2020)

    2020

  12. [12]

    Mathew, K., Montoya, J.H., Faghaninia, A., Dwarakanath, S., Aykol, M., Tang, H., Chu, I.-H., Smidt, T., Bocklund, B., Horton, M., Dagdelen, J., Wood, B., Liu, Z.-K., Neaton, J., Ong, S.P., Pers- son, K., Jain, A.: Atomate: a high-level interface to generate, execute, and analyze computational mate- rials science workflows. Comput. Mater. Sci.139, 140–152 (2017)

    2017

  13. [13]

    Preprint at https://arxiv.org/abs/2507.14267 (2025)

    Wang, Z., Huang, H., Zhao, H., Xu, C., Zhu, S., Janssen, J., Viswanathan, V.: DREAMS: density functional theory based research engine for agentic materials simulation. Preprint at https://arxiv.org/abs/2507.14267 (2025)

    arXiv 2025

  14. [14]

    Preprint at https://arxiv.org/abs/2107.03374 (2021)

    Chen, M., Tworek, J., Jun, H., Yuan, Q., Oliveira Pinto, H.P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A., Puri, R., Krueger, G., Petrov, M., Khlaaf, H., Sastry, G., Mishkin, P., Chan, B., Gray, S., Ryder, N., Pavlov, M., Power, A., Kaiser, L., Bavarian, M., Winter, C., Tillet, P., Such, F.P., Cummings, D., Plappert, M., Chantzi...

    Pith/arXiv arXiv 2021

  15. [15]

    https://openreview.net/forum?id=VTF8yNQM66

    Jimenez, C.E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., Narasimhan, K.R.: SWE- bench: can language models resolve real-world GitHub issues? The 12th International Con- ference on Learning Representations (2024). https://openreview.net/forum?id=VTF8yNQM66

    2024

  16. [16]

    Campbell, Q., Cox, S., Medina, J., Watterson, B., White, A.D.: MDCrow: automating molecular dynamics workflows with large language models. Mach. Learn.: Sci. Technol.7(2), 025037 (2026)

    2026

  17. [17]

    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp

    Wang, Y., Wang, M., Manzoor, M.A., Liu, F., Georgiev, G.N., Das, R.J., Nakov, P.: Factuality of large language models: a survey. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 19519–19529 (2024)

    2024

  18. [18]

    Buehler, M.J.: MechGPT, a language-based strat- egy for mechanics and materials modeling that connects knowledge across scales, disciplines, and modalities. Appl. Mech. Rev.76(2), 021001 (2024)

    2024

  19. [19]

    Jacobs, P.F., Pollice, R.: Developing large language models for quantum chemistry simulation input generation. Digit. Discov.4(3), 762–775 (2025) 14

    2025

  20. [20]

    Shi, Z., Xin, C., Huo, T., Jiang, Y., Wu, B., Chen, X., Qin, W., Ma, X., Huang, G., Wang, Z.,et al.: A fine-tuned large language model based molecular dynamics agent for code generation to obtain mate- rial thermodynamic parameters. Sci. Rep.15(1), 10295 (2025)

    2025

  21. [21]

    Soleymanibrojeni, M., Aydin, R., Guedes-Sobrinho, D., Dias, A.C., Piotrowski, M.J., Wenzel, W., Rˆ ego, C.R.C.: GENIUS: an agentic AI framework for autonomous design and execution of simulation protocols. Commun. Mater.7(1), 115 (2026)

    2026

  22. [22]

    Preprint at https://arxiv.org/abs/2503.21460 (2025)

    Luo, J., Zhang, W., Yuan, Y., Zhao, Y., Yang, J., Gu, Y., Wu, B., Chen, B., Qiao, Z., Long, Q., Tu, R., Luo, X., Ju, W., Xiao, Z., Wang, Y., Xiao, M., Liu, C., Yuan, J., Zhang, S., Jin, Y., Zhang, F., Wu, X., Zhao, H., Tao, D., Yu, P.S., Zhang, M.: Large language model agent: a survey on methodology, applications and challenges. Preprint at https://arxiv....

    Pith/arXiv arXiv 2025

  23. [23]

    Proceedings of the 33rd Interna- tional Joint Conference on Artificial Intelligence, pp

    Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N.V., Wiest, O., Zhang, X.: Large language model based multi-agents: a survey of progress and challenges. Proceedings of the 33rd Interna- tional Joint Conference on Artificial Intelligence, pp. 8048–8057 (2024)

    2024

  24. [24]

    In: Rogers, A., Boyd-Graber, J., Okazaki, N

    Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R.K.-W., Lim, E.-P.: Plan-and-solve prompt- ing: Improving zero-shot chain-of-thought reason- ing by large language models. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2609–2634. Asso...

    2023

  25. [25]

    Advances in Neural Information Processing Systems, vol

    Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face. Advances in Neural Information Processing Systems, vol. 36, pp. 38154– 38180 (2023)

    2023

  26. [26]

    The 13th International Conference on Learning Representations, pp

    Li, A., Xie, Y., Li, S., Tsung, F., Ding, B., Li, Y.: Agent-oriented planning in multi-agent systems. The 13th International Conference on Learning Representations, pp. 32933–32955 (2025). https://openreview.net/forum?id=EqcLAU6gyU

    2025

  27. [27]

    Advances in Neural Information Process- ing Systems, vol

    Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. Advances in Neural Information Process- ing Systems, vol. 36, pp. 8634–8652 (2023). https://openreview.net/forum?id=vAElhFcKW6

    2023

  28. [28]

    Advances in Neural Information Pro- cessing Systems, vol

    Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., Gupta, S., Majumder, B.P., Hermann, K., Welleck, S., Yazdanbakhsh, A., Clark, P.: Self-Refine: iterative refinement with self-feedback. Advances in Neural Information Pro- cessing Systems, vol. 36, pp. 46534–46594 (2023). https://openrev...

    2023

  29. [29]

    Ghafarollahi, A., Buehler, M.J.: Automating alloy design and discovery with physics-aware multimodal multiagent AI. Proc. Natl. Acad. Sci. U.S.A.122(4), 2414074122 (2025)

    2025

  30. [30]

    Matter8(7), 102263 (2025)

    Zou, Y., Cheng, A.H., Aldossary, A., Bai, J., Leong, S.X., Campos-Gonzalez-Angulo, J.A., Choi, C., Ser, C.T., Tom, G., Wang, A., Zhang, Z., Yakavets, I., Hao, H., Crebolder, C., Bernales, V., Aspuru-Guzik, A.: El Agente: an autonomous agent for quantum chemistry. Matter8(7), 102263 (2025)

    2025

  31. [31]

    Preprint at https://arxiv.org/abs/2512.23880 (2025)

    Huang, X., Chen, J., Fei, Y., Li, Z., Schwaller, P., Ceder, G.: CASCADE: cumulative agentic skill cre- ation through autonomous development and evolu- tion. Preprint at https://arxiv.org/abs/2512.23880 (2025)

    arXiv 2025

  32. [32]

    Preprint at https://arxiv.org/abs/2505.08195 (2025)

    Hu, J., Nawaz, H., Hou, Y.-F., Rui, Y., Chi, L., Chen, Y., Ullah, A., Dral, P.O.: Aitomia: your intelligent assistant for AI-driven atomistic and quantum chemical simulations. Preprint at https://arxiv.org/abs/2505.08195 (2025)

    arXiv 2025

  33. [33]

    Vriza, A., Kornu, U., Koneru, A., Chan, H., Sankaranarayanan, S.K.R.S.: Multi-agentic AI framework for end-to-end atomistic simulations. Digit. Discov.5, 440–452 (2026)

    2026

  34. [34]

    Preprint at https://arxiv.org/abs/2512.03549 (2025)

    Orimo, Y., Kurata, I., Mori, H., Okuno, R., Sawada, R., Okanohara, D.: PARC: an autonomous self-reflective coding agent for robust execution of long-horizon tasks. Preprint at https://arxiv.org/abs/2512.03549 (2025)

    arXiv 2025

  35. [35]

    Yang, F., Evans, J.D.: QUASAR: a universal autonomous system for atomistic simulation and a benchmark of its capabilities. J. Chem. Inf. Model. (2026)

    2026

  36. [36]

    Chaudhari, A., Ock, J., Barati Farimani, A.: Mod- ular large language model agents for multi-task computational materials science. Commun. Mater. 7, 131 (2026)

    2026

  37. [37]

    Preprint at https://arxiv.org/abs/2509.14542 (2025) 15

    Wang, X., Li, C., Zhang, B., Shi, J., Ran, N., Li, L., Liu, J., Zeng, D.: S1-MatAgent: a planner driven multi-agent system for material discovery. Preprint at https://arxiv.org/abs/2509.14542 (2025) 15

    arXiv 2025

  38. [38]

    In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V

    Chiang, Y., Hsieh, E., Chou, C.-H., Riebesell, J.: LLaMP: Large language model made power- ful for high-fidelity materials knowledge retrieval. In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V. (eds.) Proceedings of the 2025 Con- ference on Empirical Methods in Natural Lan- guage Processing, pp. 25189–25221. Association for Computational Lin...

    2025

  39. [39]

    Larsen, A.H., Mortensen, J.J.r., Blomqvist, J., Castelli, I.E., Christensen, R., Du lak, M., Friis, J., Groves, M.N., Hammer, B.r., Hargus, C., Hermes, E.D., Jennings, P.C., Jensen, P.B., Kermode, J., Kitchin, J.R., Kolsbjerg, E.L., Kubal, J., Kaasb- jerg, K., Lysgaard, S., Maronsson, J.B., Maxson, T., Olsen, T., Pastewka, L., Peterson, A., Rostgaard, C.,...

    2017

  40. [40]

    Mart´ ınez, L., Andrade, R., Birgin, E.G., Mart´ ınez, J.M.: PACKMOL: a package for building initial con- figurations for molecular dynamics simulations. J. Comput. Chem.30(13), 2157–2164 (2009)

    2009

  41. [41]

    Thompson, A.P., Aktulga, H.M., Berger, R., Bolin- tineanu, D.S., Brown, W.M., Crozier, P.S., in ’t Veld, P.J., Kohlmeyer, A., Moore, S.G., Nguyen, T.D., Shan, R., Stevens, M.J., Tranchida, J., Trott, C., Plimpton, S.J.: LAMMPS – a flexible simula- tion tool for particle-based materials modeling at the atomic, meso, and continuum scales. Comput. Phys. Comm...

    2022

  42. [42]

    Ramasubramani, V., Dice, B.D., Harper, E.S., Spellings, M.P., Anderson, J.A., Glotzer, S.C.: freud: a software suite for high throughput anal- ysis of particle simulation data. Comput. Phys. Commun.254, 107275 (2020)

    2020

  43. [43]

    Proceedings of the 2020 Conference on Empiri- cal Methods in Natural Language Processing, pp

    Karpukhin, V., O˘ guz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., Yih, W.-t.: Dense pas- sage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empiri- cal Methods in Natural Language Processing, pp. 6769–6781 (2020)

    2020

  44. [44]

    Sumers, T., Yao, S., Narasimhan, K.R., Griffiths, T.L.: Cognitive architectures for language agents. Trans. Mach. Learn. Res. (2024)

    2024

  45. [45]

    In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H

    Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., ...

    1901

  46. [46]

    Michaud-Agrawal, N., Denning, E.J., Woolf, T.B., Beckstein, O.: MDAnalysis: a toolkit for the analy- sis of molecular dynamics simulations. J. Comput. Chem.32(10), 2319–2327 (2011)

    2011

  47. [47]

    Proceedings of the 15th Python in Science Conference, pp

    Gowers, R.J., Linke, M., Barnoud, J., Reddy, T.J.E., Melo, M.N., Seyler, S.L., Doma´ nski, J., Dotson, D.L., Buchoux, S., Kenney, I.M., Beckstein, O.: MDAnalysis: a Python package for the rapid analy- sis of molecular dynamics simulations. Proceedings of the 15th Python in Science Conference, pp. 98–105 (2016)

    2016

  48. [48]

    Proceedings of Supercomputing, vol

    Folk, Mike and Cheng, Albert and Yates, Kim: HDF5: A file format and I/O library for high per- formance computing applications. Proceedings of Supercomputing, vol. 99, pp. 5–33 (1999)

    1999

  49. [49]

    Advances in Neural Informa- tion Processing Systems, vol

    Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K¨ uttler, H., Lewis, M., Yih, W.-t., Rockt¨ aschel, T., Riedel, S., Kiela, D.: Retrieval-augmented generation for knowledge- intensive NLP tasks. Advances in Neural Informa- tion Processing Systems, vol. 33, pp. 9459–9474 (2020)

    2020

  50. [50]

    Preprint at https://arxiv.org/abs/2312.10997 (2023)

    Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., Wang, H.: Retrieval-augmented generation for large language models: a survey. Preprint at https://arxiv.org/abs/2312.10997 (2023)

    Pith/arXiv arXiv 2023

  51. [51]

    Preprint at https://arxiv.org/abs/2407.21787 (2024)

    Brown, B., Juravsky, J., Ehrlich, R., Clark, R., Le, Q.V., R´ e, C., Mirhoseini, A.: Large language mon- keys: scaling inference compute with repeated sam- pling. Preprint at https://arxiv.org/abs/2407.21787 (2024)

    Pith/arXiv arXiv 2024

  52. [52]

    Green, M.S.: Markoff random processes and the sta- tistical mechanics of time-dependent phenomena. ii. irreversible processes in fluids available to purchase. J. Chem. Phys.22(3), 398–413 (1954)

    1954

  53. [53]

    Kubo, R.: Statistical-mechanical theory of irre- versible processes. i. general theory and simple applications to magnetic and conduction problems. J. Phys. Soc. Jpn.12(6), 570–586 (1957)

    1957

  54. [54]

    ACS Appl

    Choi, J.M., Kim, J., Lee, J.-H., Son, W.-J., Han, S.: 16 Atomistic insights into Cu/amorphous-Ta xN inter- facial adhesion via machine learning interatomic potentials: effects of stoichiometry and interface construction. ACS Appl. Electron. Mater.7(24), 11165–11179 (2025)

    2025

  55. [55]

    Wilson, E.B.: Probable inference, the law of succes- sion, and statistical inference. J. Am. Stat. Assoc. 22(158), 209–212 (1927). Accessed 2026-05-22

    1927

  56. [56]

    Newcombe, R.G.: Two-sided confidence intervals for the single proportion: comparison of seven methods. Stat. Med.17(8), 857–872 (1998)

    1998

  57. [57]

    The 39th Annual Conference on Neural Information Processing Systems (2025)

    Wood, B.M., Dzamba, M., Fu, X., Gao, M., Shuaibi, M., Barroso-Luque, L., Abdelmaqsoud, K., Gharakhanyan, V., Kitchin, J.R., Levine, D.S., Michel, K., Sriram, A., Cohen, T., Das, A., Sahoo, S.J., Rizvi, A., Ulissi, Z.W., Zit- nick, C.L.: UMA: A family of universal mod- els for atoms. The 39th Annual Conference on Neural Information Processing Systems (2025...

    2025

  58. [58]

    et al.: OpenAI GPT-5 System Card (2026)

    Singh, A. et al.: OpenAI GPT-5 System Card (2026). https://arxiv.org/abs/2601.03267

    Pith/arXiv arXiv 2026

  59. [59]

    Ope- nAI Deployment Safety Hub

    OpenAI: GPT-5.4 Thinking System Card. Ope- nAI Deployment Safety Hub. Accessed: 2026-05- 22 (2026). https://deploymentsafety.openai.com/ gpt-5-4-thinking

    2026

  60. [60]

    The 11th International Conference on Learning Representations (2023)

    Wang, X., Wei, J., Schuurmans, D., Le, Q.V., Chi, E.H., Narang, S., Chowdhery, A., Zhou, D.: Self-consistency improves chain of thought reason- ing in language models. The 11th International Conference on Learning Representations (2023). https://openreview.net/forum?id=1PL1NIMMrw

    2023

  61. [61]

    Ju, S., You, J., Kim, G., Park, Y., An, H., Han, S.: Application of pretrained universal machine- learning interatomic potential for physicochemical simulation of liquid electrolytes in Li-ion batteries. Digit. Discov.4(6), 1544–1559 (2025)

    2025

  62. [62]

    The 13th International Con- ference on Learning Representations (2025)

    Snell, C.V., Lee, J., Xu, K., Kumar, A.: Scal- ing LLM test-time compute optimally can be more effective than scaling model parameters for reasoning. The 13th International Con- ference on Learning Representations (2025). https://openreview.net/forum?id=4FWAwZtd2n

    2025

  63. [63]

    Schappals, M., Mecklenfeld, A., Kr¨ oger, L.C., Botan, V.A., K¨ oster, A., Stephan, S., Garcia, E.J., Rutkai, G., Raabe, G., Klein, P., Leonhard, K., Glass, C.W., Lenhard, J., Vrabec, J., Hasse, H.: Round robin study: molecular simulation of ther- modynamic properties from models with internal degrees of freedom. J. Chem. Theory Comput. 13(9), 4270–4280 (2017)

    2017

  64. [64]

    APL Mater

    Jain, A., Ong, S.P., Hautier, G., Chen, W., Richards, W.D., Dacek, S., Cholia, S., Gunter, D., Skinner, D., Ceder, G., Persson, K.A.: Commentary: the Materials Project: a materials genome approach to accelerating materials innovation. APL Mater. 1(1), 011002 (2013)

    2013

  65. [65]

    npj Comput

    Kim, J., Lee, J., Oh, S., Park, Y., Hwang, S., Han, S., Kang, S., Kang, Y.: An efficient forgetting- aware fine-tuning framework for pretrained uni- versal machine-learning interatomic potentials. npj Comput. Mater.12, 26 (2026)

    2026

  66. [66]

    Preprint at https://arxiv.org/abs/2505.00753 (2025)

    Zou, H.P., Huang, W.-C., Wu, Y., Guo, J., Chen, Y., Miao, C., Nguyen, H., Zhou, Y., Zhang, W., Fang, L., Zhang, H., Wang, F., Zhang, P., Wang, H., He, L., Li, Y., Li, D., Jiang, R., Liu, X., Yu, P.S.: LLM-based human-agent collaboration and interaction systems: a survey. Preprint at https://arxiv.org/abs/2505.00753 (2025)

    Pith/arXiv arXiv 2025

  67. [67]

    Preprint at https://arxiv.org/abs/2502.18864 (2025)

    Gottweis, J., Weng, W.-H., Daryin, A., Tu, T., Palepu, A., Sirkovic, P., Myaskovsky, A., Weis- senberger, F., Rong, K., Tanno, R., Saab, K., Popovici, D., Blum, J., Zhang, F., Chou, K., Has- sidim, A., Gokturk, B., Vahdat, A., Kohli, P., Matias, Y., Carroll, A., Kulkarni, K., Tomasev, N., Guan, Y., Dhillon, V., Vaishnav, E.D., Lee, B., Costa, T.R.D., Pena...

    Pith/arXiv arXiv 2025

  68. [68]

    Accessed: 2026-05-17 (2024)

    Anthropic: Model Context Protocol: Intro- duction. Accessed: 2026-05-17 (2024). https: //modelcontextprotocol.io/docs/getting-started/ intro

    2026

  69. [69]

    https://github.com/ jerryjliu/llama index

    Liu, J.: LlamaIndex, (2022). https://github.com/ jerryjliu/llama index

    2022

  70. [70]

    In: Croft, B.W., van Rijs- bergen, C.J

    Robertson, S.E., Walker, S.: Some simple effective approximations to the 2-Poisson model for proba- bilistic weighted retrieval. In: Croft, B.W., van Rijs- bergen, C.J. (eds.) Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 232–

  71. [71]

    Springer, London (1994)

    1994

  72. [72]

    Proceedings of the 32nd Annual International ACM SIGIR Confer- ence on Research and Development in Information Retrieval, pp

    Cormack, G.V., Clarke, C.L.A., Buettcher, S.: Reciprocal rank fusion outperforms Condorcet and individual rank learning methods. Proceedings of the 32nd Annual International ACM SIGIR Confer- ence on Research and Development in Information Retrieval, pp. 758–759 (2009) 17

    2009

  73. [73]

    Tai, S.T., Wang, C., Cheng, R., Chen, Y.: Revisit- ing many-body interaction heat current and thermal conductivity calculations using the moment ten- sor potential/lammps interface. J. Chem. Theory Comput.21(7), 3649–3657 (2025)

    2025

  74. [74]

    Mantina, M., Chamberlin, A.C., Valero, R., Cramer, C.J., Truhlar, D.G.: Consistent van der Waals radii for the whole main group. J. Phys. Chem. A 113(19), 5806–5812 (2009)

    2009

  75. [75]

    Evans, D.J., Holian, B.L.: The Nose–Hoover ther- mostat. J. Chem. Phys.83(8), 4069–4074 (1985)

    1985

  76. [76]

    Martyna, G.J., Tobias, D.J., Klein, M.L.: Constant pressure molecular dynamics algorithms. J. Chem. Phys.101(5), 4177–4189 (1994)

    1994

  77. [77]

    Shinoda, W., Shiga, M., Mikami, M.: Rapid esti- mation of elastic constants by molecular dynamics simulation under constant stress. Phys. Rev. B69, 134103 (2004)

    2004

  78. [78]

    Oxford University Press, Oxford (2017)

    Allen, M.P., Tildesley, D.J.: Computer Simulation of Liquids, 2nd edn. Oxford University Press, Oxford (2017)

    2017

  79. [79]

    npj Comput

    He, X., Zhu, Y., Epstein, A., Mo, Y.: Statistical vari- ances of diffusional properties from ab initio molecu- lar dynamics simulations. npj Comput. Mater.4(1), 18 (2018)

    2018

  80. [80]

    In: Singh, A., Fazel, M., Hsu, D., Lacoste-Julien, S., Berkenkamp, F., Maharaj, T., Wagstaff, K., Zhu, J

    Lee, S.Y., Kim, H., Park, Y., Jeong, D., Han, S., Park, Y., Lee, J.W.: FlashTP: Fused, sparsity- aware tensor product for machine learning inter- atomic potentials. In: Singh, A., Fazel, M., Hsu, D., Lacoste-Julien, S., Berkenkamp, F., Maharaj, T., Wagstaff, K., Zhu, J. (eds.) Pro- ceedings of the 42nd International Conference on Machine Learning. Proceed...

    2025

Showing first 80 references.