Thang D. Pham

Argonne National Laboratory

Lemont, IL 60439

I am Thang Pham, a postdoctoral researcher at Argonne National Laboratory. My work centers on agentic AI systems for scientific discovery, where I design multi-agent workflows and scalable agentic pipelines that run on leadership-class HPC systems and let scientists plan, reason about, and execute complex computational experiments through natural language.

I build AI systems that interface directly with the scientific stack: simulation codes (DFT, Monte Carlo, machine-learning interatomic potentials, molecular dynamics), databases and retrieval tools, HPC schedulers, and workflow engines. A central thread of my research is making autonomous, large-scale discovery workflows both practical and trustworthy, including frameworks for evaluating how well AI agents actually perform on real scientific tasks.

I earned my Ph.D. in Chemical and Biological Engineering at Northwestern University in the Snurr group, where I applied molecular simulation, machine learning, and optimization to materials (metal-organic frameworks) discovery, including carbon dioxide capture, hydrogen storage, water harvesting, and photocatalysis. That background in computational materials science is the domain I now bring agentic AI to, with the goal of developing data-driven solutions that have a real impact on society.

news

Jun 26, 2026	I presented “Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System” at The 2nd International Workshop on Foundational Large Language Models Advances for HPC at ISC High Performance 2026 workshop in Hamburg, Germany.
Jan 15, 2026	Our paper “ChemGraph as an agentic framework for computational chemistry workflows” was published in Communications Chemistry.
Jul 01, 2025	I presented ChemGraph: An Agentic Framework for Computational Chemistry at the Trillion Parameter Consortium (TPC25) in San Jose, CA.
Dec 02, 2024	I started as a Postdoctoral Researcher at Argonne National Laboratory, working on agentic AI systems for scientific discovery.
Sep 15, 2024	I defended my Ph.D. and completed my degree in Chemical and Biological Engineering at Northwestern University. 🎓

selected publications

Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System

Thang Duc Pham, Harikrishna Tummalapalli, Fakhrul Hasan Bhuiyan, and 5 more authors

2026

Bib HTML

@misc{pham2026multiagent,
  title = {Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System},
  author = {Pham, Thang Duc and Tummalapalli, Harikrishna and Bhuiyan, Fakhrul Hasan and V{\'a}zquez Mayagoitia, {\'A}lvaro and Simpson, Christine and Balin, Riccardo and Vishwanath, Venkatram and Ke{\c{c}}eli, Murat},
  year = {2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
}

ChemGraph as an agentic framework for computational chemistry workflows

Thang D. Pham, Aditya Tanikanti, and Murat Keçeli

Communications Chemistry, 2026

Abs DOI Bib HTML

ChemGraph is an agentic framework powered by AI and state-of-the-art simulation tools to streamline and automate computational chemistry and materials science workflows, combining graph neural network foundation models with large language models for planning and scientific reasoning.
@article{pham_chemgraph_2026, title = {ChemGraph as an agentic framework for computational chemistry workflows}, author = {Pham, Thang D. and Tanikanti, Aditya and Ke{\c{c}}eli, Murat}, journal = {Communications Chemistry}, year = {2026}, publisher = {Nature Publishing Group}, doi = {10.1038/s42004-025-01776-9}, }

Implementation of Genetic Algorithms to Optimize Metal-Organic Frameworks for CO2 Capture

Thang D. Pham and Randall Q. Snurr

Langmuir, 2025

DOI Bib HTML

@article{pham_implementation_2025,
  title = {Implementation of Genetic Algorithms to Optimize Metal-Organic Frameworks for CO2 Capture},
  author = {Pham, Thang D. and Snurr, Randall Q.},
  journal = {Langmuir},
  volume = {41},
  number = {7},
  pages = {4585--4593},
  year = {2025},
  publisher = {American Chemical Society},
  doi = {10.1021/acs.langmuir.4c04386},
}

CoRE MOF DB: A curated experimental metal-organic framework database with machine-learned properties for integrated material-process screening

Guobin Zhao, Logan M. Brabson, Saumil Chheda, and 17 more authors

Matter, 2025

DOI Bib HTML

@article{zhao_core_2025,
  title = {CoRE MOF DB: A curated experimental metal-organic framework database with machine-learned properties for integrated material-process screening},
  author = {Zhao, Guobin and Brabson, Logan M. and Chheda, Saumil and Huang, Ju and Kim, Haewon and Liu, Kunhuan and Mochida, Kenji and Pham, Thang D. and Prerna and Terrones, Gianmarco G. and Yoon, Sunghyun and Zoubritzky, Lionel and Coudert, Fran{\c{c}}ois-Xavier and Haranczyk, Maciej and Kulik, Heather J. and Moosavi, Seyed Mohamad and Sholl, David S. and Siepmann, J. Ilja and Snurr, Randall Q. and Chung, Yongchul G.},
  journal = {Matter},
  volume = {8},
  number = {6},
  year = {2025},
  publisher = {Elsevier},
  doi = {10.1016/j.matt.2025.102140},
}

Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks

Yigitcan Comlek, Thang Duc Pham, Randall Q. Snurr, and 1 more author

npj Computational Materials, 2023

DOI Bib HTML

@article{comlek2023rapid,
  title = {Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks},
  author = {Comlek, Yigitcan and Pham, Thang Duc and Snurr, Randall Q. and Chen, Wei},
  journal = {npj Computational Materials},
  volume = {9},
  number = {1},
  pages = {170},
  year = {2023},
  publisher = {Nature Publishing Group UK London},
  doi = {10.1038/s41524-023-01125-1},
}