上海 AI Lab 发布 DrugHarness 智能体，亲和对比精度提升 10.8pp，Hits@3 提升 55%
药化 agent 别只会调工具：上海 AI Lab DrugHarness，亲和对比 +10.8pp，Hits@3 +55%，进化后 Qwen 62.2→81.1%
上海 AI Lab 发布了 DrugHarness 智能体，该智能体在药物发现任务中实现了显著的性能提升，亲和对比精度提升了 10.8pp，Hits@3 提升了 55%。
DrugHarness 智能体在药物发现任务中展现出显著的性能提升，其研究成果对科学智能体和计算药物设计领域具有重要意义。
Authors:Yuxing Chen, Zhisheng Zhang, Cheng Tang, Wei Li, Minghui Zhang, Ziyan Huang, Shaocong Wei, Jiawei Chen, Junru Hu, Hongze Zhu, Jianghan Shen, Min Cen, Xinyuan Zhu, Yaxue Zhao, Jubo Wang, Yuqiang Li, Chun-Mei Feng, Zongyuan Ge, Rui Su, Jie Xu, Yirong Chen, Xi Xu, Ming Hu
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.23791 [cs.AI] |
| (or arXiv:2610.23791v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23791 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuxing Chen [view email]
[v1]
Fri, 16 Oct 2026 17:20:19 UTC (1,901 KB)
来源：Agent Control Flash News · arxiv.org
Cursor Agent 架构全景拆解：从影子工作区到多文件推演引擎
全面剖析 Cursor 在 Agent 模式下的底层技术实现，解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。
Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览
动态速评：v0 正在从单一组件生成器演进为全栈应用搭建协作台，尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。