Preprint · 2025 · Open access
DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
Research Square · Published 29 September 2025 · DOI 10.21203/rs.3.rs-7489358/v1
In brief
“DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery” is a 2025 preprint by Wenbin Hu and 7 co-authors, published in Research Square. OpenAlex counts 33 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.
- Citations
- 33
- Most cited in
- 2026 (25)
- References
- 91
- Authors
- 8
Abstract
Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution. However, applying LLM agents to drug discovery is still constrained by challenges such as large-scale multimodal data processing, limited task automation, and poor support for domain-specific tools. To overcome these limitations, we introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific workflows in drug discovery. DrugPilot enables multi-stage research processes by integrating structured tool use with a novel parameterized memory pool. The memory pool converts heterogeneous data from both public sources and user-defined inputs into standardized representations. This design supports efficient multi-turn conversation, reduces information loss during data exchange, and enhances complex scientific decision-making. To support training and benchmarking, we construct a drug instruction dataset covering eight core drug discovery tasks. Under the Berkeley function-calling benchmark, DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn categories, respectively. These results highlight DrugPilot's strong potential as a generalizable agent framework for automated, interactive, and data-driven reasoning across computational science applications.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hu, W., Li, K., Wu, Z., Wang, S., Wu, J. X., Du, B., Wang, X., & Pan, S. (2025). DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery. Research Square. https://doi.org/10.21203/rs.3.rs-7489358/v1
MLA 9
Hu, Wenbin, et al. “DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery.” Research Square, 2025. https://doi.org/10.21203/rs.3.rs-7489358/v1.
Chicago
Hu, Wenbin, Kun Li, Zhennan Wu, Shoupeng Wang, Jia Xin Wu, Bo Du, Xiangyu Wang, and Shirui Pan. 2025. “DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery.” Research Square. https://doi.org/10.21203/rs.3.rs-7489358/v1.
Harvard
Hu, W. et al. (2025) ‘DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery’, Research Square. doi:10.21203/rs.3.rs-7489358/v1.
IEEE
W. Hu et al., “DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery,” Research Square, 2025, doi: 10.21203/rs.3.rs-7489358/v1.
BibTeX
@misc{hu2025drugpilot,
title = {{DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery}},
author = {Hu, Wenbin and Li, Kun and Wu, Zhennan and Wang, Shoupeng and Wu, Jia Xin and Du, Bo and Wang, Xiangyu and Pan, Shirui},
howpublished = {Research Square},
year = {2025},
doi = {10.21203/rs.3.rs-7489358/v1},
url = {https://doi.org/10.21203/rs.3.rs-7489358/v1}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- LLM agents
- drug discovery
- memory pool
- tool use
- multi-turn dialogue
- multimodal processing
Work with this paper
Most-cited papers in Pharmacology, Toxicology and Pharmaceutics
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingOleg Trott, Arthur J. Olson · Journal of Computational Chemistry · 2009 · 39,860 citations
- AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibilityGarrett M. Morris, Ruth Huey, William Lindstrom and 4 more · Journal of Computational Chemistry · 2009 · 26,508 citations
- Development and testing of a general amber force fieldJunmei Wang, Romain M. Wolf, James W. Caldwell and 2 more · Journal of Computational Chemistry · 2004 · 20,080 citations
- Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings 1PII of original article: S0169-409X(96)00423-1. The article was originally published in Advanced Drug Delivery Reviews 23 (1997) 3–25. 1Christopher A. Lipinski, Franco Lombardo, Beryl W. Dominy and 1 more · Advanced Drug Delivery Reviews · 2001 · 19,638 citations
- SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small moleculesAntoine Daina, Olivier Alain Michielin, Vincent Zoete · Scientific Reports · 2017 · 19,557 citations
All highly cited Pharmacology, Toxicology and Pharmaceutics papers
Questions about this paper
How do I cite this paper in APA style?
Hu, W., Li, K., Wu, Z., Wang, S., Wu, J. X., Du, B., Wang, X., & Pan, S. (2025). DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery. Research Square. https://doi.org/10.21203/rs.3.rs-7489358/v1
How many times has this paper been cited?
33 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Research Square: sign in and open the PDF from this page.
Who wrote this paper?
Wenbin Hu, Kun Li, Zhennan Wu, Shoupeng Wang, Jia Xin Wu, Bo Du, Xiangyu Wang, Shirui Pan.
What is the DOI of this paper?
10.21203/rs.3.rs-7489358/v1, permanently at https://doi.org/10.21203/rs.3.rs-7489358/v1. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.