AgentDrug: Utilizing Large Language Models in an Agentic Workflow for Zero-Shot Molecular Optimization
This work addresses the problem of low accuracy in molecular optimization for drug discovery using LLMs, offering a novel agentic approach that is incremental but shows strong performance gains.
The paper tackles molecular optimization in drug discovery by proposing AgentDrug, an agentic workflow that uses large language models in a structured refinement process, achieving accuracy improvements of up to 29.0% on single-property tasks and up to 14.9% on multi-property tasks compared to previous methods.
Molecular optimization -- 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 optimization, straightforward prompting achieves limited accuracy. In this work, we propose AgentDrug, an 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. We evaluate AgentDrug on benchmarks with both single- and multi-property optimization under loose and strict thresholds. Results demonstrate significant performance gains over previous methods. With Qwen-2.5-3B, AgentDrug improves accuracy by 20.7\% (loose) and 16.8\% (strict) on six single-property tasks, and by 7.0\% and 5.3\% on eight multi-property tasks. With larger model Qwen-2.5-7B, AgentDrug further improves accuracy on 6 single-property objectives by 28.9\% (loose) and 29.0\% (strict), and on 8 multi-property objectives by 14.9\% (loose) and 13.2\% (strict).