AgentDrug
Molecular editing—modifying a given molecule to improve desired properties—is a fundamental task in drug discovery. While LLMs hold the potential to solve this task using natural language to drive the editing, straightforward prompting achieves limited accuracy. AgentDrug is anan agentic workflow that leverages LLMs in a structured refinement process to achieve significantly higher accuracy. AgentDrug defines a nested refinement loop: the inner loop uses feedback from cheminformatics toolkits to validate molecular structures, while the outer loop guides the LLM with generic feedback and a gradient-based objective to steer the molecule toward property improvement.
Publications
- Le, K.; Hua, T.; Chawla, N. V. AgentDrug: Utilizing Large Language Models in an Agentic Workflow for Zero-Shot Molecular Editing Conf. Emp. Meth. Natural Lang. Proc (EMNLP2025) 2025 24448–24458. https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.1328.pdf