让药物发现模型学会总结经验，一次积累，多次复用。
DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
- 构建跨任务记忆库，记录有效策略与错误修复方法。
- 在33个任务中单次任务设置排名第一，跨任务平均得分0.935。
- 可直接复用已有方案，无需重新搜索，适合高效研发场景。
构建先进的药物发现预测模型需要昂贵的工具、架构和训练策略搜索。当前基于大语言模型的智能体虽能通过大量试错找到最优解，但无法保留过程中积累的经验，导致每个新任务都需重头开始。我们提出 method（Self-evolving Agent Experience），一个通过跨任务积累并复用经验的框架，以高效构建最先进的药物发现模型。该框架维护跨任务的记忆：已验证技能、有效策略的统计证据，以及常见错误及其修正记录。在某些情况下，可直接转移已成功方案而无需测试时搜索。在33个分子属性预测任务中， method 在单任务设置下超越九种现有SOTA智能体。在跨任务评估中，利用16个小型任务积累的记忆，在17个保留任务上实现平均归一化得分0.935，并在零测试时搜索条件下比所有基线智能体提升10%-30%。结果表明，跨任务记忆在药物发现中实现高效SOTA建模具有显著优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。