PharmAgents2: Towards Autonomous End-to-End Drug Discovery
Abstract
Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug discovery that combines knowledge-enhanced decision-making with organized large-scale exploration. Paper2Skill extracts transferable scientific decision knowledge from public sources and, together with expert-developed skills, supports research decisions. Self-Scaling Discovery expands exploration through parallel agents inheriting research context and decision-making capabilities across targets, scientific hypotheses, and discovery strategies. We introduce PharmAgents-Bench v0.1, comprising 121 questions across nine decision scenarios and three end-to-end tasks assessed with expert-defined process rubrics. PharmAgents2 outperforms evaluated baselines in most decision categories and achieves the highest process scores on all three end-to-end tasks. In three real-world studies, autonomous investigations generated findings subsequently supported by human-executed experiments. For LpxH, PharmAgents2 hypothesized a previously unreported allosteric site and screened compounds against it, identifying a novel inhibitor scaffold with experimentally confirmed inhibitory activity and binding. For JAK1, it prioritized a covalent inhibition strategy and nominated compounds with experimentally demonstrated activity. Starting from a known bioactive molecule, Self-Scaling Discovery explored candidate targets across the proteome and identified a new binding target, with the interaction subsequently confirmed experimentally. PharmAgents2 represents a prototype of a virtual pharmaceutical company, marking a step toward autonomous end-to-end drug discovery.
Related
- A Closed-Loop Robot Scientist for Autonomous Biological Discovery
- Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer's Disease Drug Discovery
- Target Discovery and Drug Intervention in Inflammatory Diseases： A Paradigm Shift from Mechanistic Dissection to Precision Therapy
- Fragment-based drug discovery strategy reveals an unprecedented allosteric binding site in Mycobacterium tuberculosis DNA gyrase
- High-throughput platforms for genetic perturbation screening using CRISPR/Cas9 in human iPSC-derived macrophages for drug discovery
BibTeX
@misc{tan2026pharmagents2,
title = {{PharmAgents2: Towards Autonomous End-to-End Drug Discovery}},
author = {Haichuan Tan and Bowen Gao and Tao Huang and Jiaxin Tan and Xin Hong and Baoguo Yao and Yifei Wang and Zhichao Deng and Hanji Du and Dapeng Jiang and Yiheng Li and Weiwei Ma and Xin Ma and Yuqi Shi and Zixiang Wang and Kelin Wu and Tianxiang Wu and Wenxuan Xie and Jie Zang and Huiyu Zhang and Mojia Zhang and Yuying Zhang and Ya-Qin Zhang and Wei-Ying Ma and Yanyan Lan},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07653},
eprint = {2611.07653},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07653},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - PharmAgents2: Towards Autonomous End-to-End Drug Discovery
AU - Haichuan Tan
AU - Bowen Gao
AU - Tao Huang
AU - Jiaxin Tan
AU - Xin Hong
AU - Baoguo Yao
AU - Yifei Wang
AU - Zhichao Deng
AU - Hanji Du
AU - Dapeng Jiang
AU - Yiheng Li
AU - Weiwei Ma
AU - Xin Ma
AU - Yuqi Shi
AU - Zixiang Wang
AU - Kelin Wu
AU - Tianxiang Wu
AU - Wenxuan Xie
AU - Jie Zang
AU - Huiyu Zhang
AU - Mojia Zhang
AU - Yuying Zhang
AU - Ya-Qin Zhang
AU - Wei-Ying Ma
AU - Yanyan Lan
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.07653
UR - https://arxiv.org/abs/2611.07653
AB - Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug discovery that combines knowledge-enhanced decision-making with organized large-scale exploration. Paper2Skill extracts transferable scientific decision knowledge from public sources and, together with expert-developed skills, supports research decisions. Self-Scaling Discovery expands exploration through parallel agents inheriting research context and decision-making capabilities across targets, scientific hypotheses, and discovery strategies. We introduce PharmAgents-Bench v0.1, comprising 121 questions across nine decision scenarios and three end-to-end tasks assessed with expert-defined process rubrics. PharmAgents2 outperforms evaluated baselines in most decision categories and achieves the highest process scores on all three end-to-end tasks. In three real-world studies, autonomous investigations generated findings subsequently supported by human-executed experiments. For LpxH, PharmAgents2 hypothesized a previously unreported allosteric site and screened compounds against it, identifying a novel inhibitor scaffold with experimentally confirmed inhibitory activity and binding. For JAK1, it prioritized a covalent inhibition strategy and nominated compounds with experimentally demonstrated activity. Starting from a known bioactive molecule, Self-Scaling Discovery explored candidate targets across the proteome and identified a new binding target, with the interaction subsequently confirmed experimentally. PharmAgents2 represents a prototype of a virtual pharmaceutical company, marking a step toward autonomous end-to-end drug discovery.
ER -