🧑‍🔬 Andrew D White

🏛️ Affiliations

🎓University of RochesterRochester · United States2015–2025 · 51 papersEmployment since 2015 · Assistant Professor, Chemical Engineering🎓University of WashingtonSeattle · United States2008–2014 · 14 papersEducation 2008–2013 · Doctor of Philosophy, Chemical Engineering🤝Future House, Inc.San Francisco · United States2024–2025 · 5 papers🎓University of ChicagoChicago · United States2013–2018 · 4 papersEmployment 2013–2014 · Postdoctoral Researcher with Prof Gregory A. Voth, Chemistry & Institute for Biophysical Dynamics🎓Cornell UniversityIthaca · United States1984–2002 · 2 papers

🏛️FutureHouseSan Francisco · United States2023Employment since 2023 · Head of Science

🎓Rose–Hulman Institute of TechnologyTerre Haute · United States2004–2008Education 2004–2008 · Bachelor of Science, Magna Cum Laude, Chemical Engineering

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. A Review of Large Language Models and Autonomous Agents in Chemistry (2024 · 288 citations)
   Chemistry faces four linked bottlenecks: predicting properties of candidate compounds, generating molecules that meet target profiles (inverse design), planning efficient syntheses, and automating lab work.
2. ChemCrow: Augmenting large-language models with chemistry tools (2023 · 211 citations)
   General-purpose LLMs such as GPT-4 often fail at chemistry. They cannot reliably convert IUPAC names into structures, and they have no access to specialised software or databases. Meanwhile, many strong computational chemistry tools exist, but non-programmers find them hard to combine. ChemCrow addresses both…
3. PaperQA: Retrieval-Augmented Generative Agent for Scientific Research (2023 · 109 citations)
   Scientific literature grows faster than researchers can read it, and plain LLMs answering science questions tend to invent facts, give no traceable sources, and know nothing published after their training cutoff.
4. Language agents achieve superhuman synthesis of scientific knowledge (2024 · 89 citations)
   Can LLM-based systems be trusted to search, summarize, and critically examine scientific literature? The authors address this with an evaluation framework that compares an AI agent directly against PhD-level experts on three realistic tasks: answering questions that require retrieval from full-text papers, writing…
5. LAB-Bench: Measuring Capabilities of Language Models for Biology Research (2024 · 62 citations)
   Most science benchmarks for LLMs test textbook-style recall, not the practical work researchers do every day. LAB-Bench, from FutureHouse, fills this gap for biology. It contains more than 2,400 multiple-choice questions covering:

All works

7 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. A Review of Large Language Models and Autonomous Agents in ChemistryarXiv:2407.01603Mayk Caldas Ramos, Christopher J. Collison, Andrew D. White2024 · 288 citations
2. ChemCrow: Augmenting large-language models with chemistry toolsarXiv:2304.05376Andres M Bran, Sam Cox, Oliver Schilter, et al.2023 · 211 citations
3. PaperQA: Retrieval-Augmented Generative Agent for Scientific ResearcharXiv:2312.07559Jakub Lála, Odhran O'Donoghue, Aleksandar Shtedritski, et al.2023 · 109 citations
4. Language agents achieve superhuman synthesis of scientific knowledgearXiv:2409.13740Michael D. Skarlinski; Sam Cox; Jon M. Laurent; James D. Braza; Michaela Hinks; Michael J. Hammerling; Manvitha Ponnapati; Samuel G. Rodriques;, Andrew D. White2024 · 89 citations
5. LAB-Bench: Measuring Capabilities of Language Models for Biology ResearcharXiv:2407.10362Jon M. Laurent, Joseph D. Janizek, Michael Ruzo, et al.2024 · 62 citations
6. Kosmos: An AI Scientist for Autonomous Discovery ↗arXiv:2511.02824 · no summary yetLudovico Mitchener; Angela Yiu; Benjamin Chang; Mathieu Bourdenx; Tyler Nadolski; Arvis Sulovari; Eric C. Landsness; Daniel L. Barabasi; Siddharth Narayanan; Nicky Evans; Shriya Reddy; Martha Foiani; Aizad Kamal; Leah P. Shriver; Fang Cao; Asmamaw T. Wassie; Jon M. Laurent; Edwin Melville-Green; Mayk Caldas; Albert Bou; Kaleigh F. Roberts; Sladjana Zagorac; Timothy C. Orr; Miranda E. Orr; Kevin J. Zwezdaryk; Ali E. Ghareeb; Laurie McCoy; Bruna Gomes; Euan A. Ashley; Karen E. Duff; Tonio Buonassisi; Tom Rainforth; Randall J. Bateman; Michael Skarlinski; Samuel G. Rodriques; Michaela M. Hinks;, Andrew D. White2025 · 29 citations
7. Aviary: training language agents on challenging scientific tasks ↗arXiv:2412.21154 · no summary yetSiddharth Narayanan et al.2024 · 18 citations

🤝 Co-authors here

2 co-authors with a page, the most papers together first.

• Sam Cox ×2
• Samuel G. Rodriques ×2

🔗 Cited by

Papers of our library cite their works 277 times (of the 149,439 papers whose bibliographies we read); 64 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/andrew-d-white/