DrugHarness 发布：可进化的药物发现智能体框架
DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
这个智能体框架专门给药物研发用，会自己从实验轨迹里学新技能，拿 Qwen 跑出来的准确率能提近 19 个百分点，还能和真实湿实验对上。
DrugHarness 是一个面向计算药物发现的可进化智能体框架，集成了 80 多个科学操作与生物医药资源。它能从执行轨迹中归纳技能假设，由独立审查智能体验证后纳入后续任务。在 MolBench 上，未进化的 DrugHarness 比已报告的 MolClaw-CC 结果在亲和力比较准确率上高出 10.8 个百分点。技能进化使 Qwen 的亲和力比较准确率从 62.2% 提升至 81.1%，优化成功率从 79.5% 提升至 87.2%。在一项 HPK1 前瞻性研究中，合成化合物实现了 14.19 nM 的细胞 IC50，效力比最佳参考分子提高 2.64 倍。
DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execution with conditional skill induction. Its environment integrates over 80 scientific operations, biomedical resources and task-specific code, preserving associations among candidates, results and artifacts. From execution trajectories and outcome feedback, DrugHarness induces action hypotheses with observable applicability conditions, recommended actions and supporting evidence. An independent review agent evaluates candidate skills derived from these hypotheses through source verification and, when needed, targeted execution trials. Admitted skills guide subsequent tasks and are revised through feedback. Evaluation on MolBench and SMDD-Bench demonstrates capabilities in molecular screening, optimization and constrained design. Without evolution, DrugHarness exceeds reported MolClaw-CC results by 10.8 percentage points in affinity-comparison accuracy and 55% in mean top-three active hits on MolBench. Retrospective evaluation on skill-development tasks shows that evolution increases Qwen's affinity-comparison accuracy from 62.2% to 81.1% and optimization success from 79.5% to 87.2%. In a prospective HPK1 study, DrugHarness achieves a more favorable median docking score than Biomni among system-specific candidates. A synthesized compound achieves a cellular IC50 of 14.19 nM, a 2.64-fold potency improvement over the best input reference, with activity competitive with two selected compounds designed by experienced medicinal chemists. These results support conditional skill evolution for scientific agents and demonstrate a workflow connecting computational drug design with experimental validation.
