DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
This work addresses the high cost of building SOTA models for drug discovery by enabling LLM-based agents to retain and reuse experience across tasks, significantly improving efficiency.
DrugSAGE introduces a self-evolving agent that accumulates and reuses cross-task experience to build state-of-the-art drug discovery models efficiently. It achieves an averaged normalized score of 0.935 on 17 held-out tasks, outperforming baseline agents by 10-30% in zero-test-time search.
Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Current LLM-based agents can find SOTA solutions through extensive trial and error, but they do not retain the experience accumulated along the way and therefore pay the full search cost on every new task. We propose \method (Self-evolving Agent Experience), a framework that accumulates and reuses experience across tasks to build SOTA drug discovery models efficiently. \method maintains a cross-task memory of verified skills, statistical evidence about effective strategies, and a record of recurring errors and their fixes. In some cases, \method transfers a working solution directly without test-time search. In 33 molecular property prediction tasks, \method ranks first among nine SOTA agents in a single-task setting. With memory accumulated from 16 smaller tasks, \method achieves an averaged normalized score of 0.935 on 17 held-out tasks in a cross-task evaluation setting and outperforms all baseline agents by 10-30\% in a zero-test-time search regime. In summary, our work shows the advantage of cross-task memory for efficient SOTA model development in drug discovery.