MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916019762626560 |
|---|---|
| author | Zhang, Lisheng Wang, Lilong Sun, Xiangyu Tang, Wei Su, Haoyang Qian, Yuehui Yang, Qikui Li, Qingsong Tang, Zhenyu Sun, Haoran Han, Yingnan Jiang, Yankai Lou, Wenjie Zhou, Bowen Wang, Xiaosong Bai, Lei Xie, Zhengwei |
| author_facet | Zhang, Lisheng Wang, Lilong Sun, Xiangyu Tang, Wei Su, Haoyang Qian, Yuehui Yang, Qikui Li, Qingsong Tang, Zhenyu Sun, Haoran Han, Yingnan Jiang, Yankai Lou, Wenjie Zhou, Bowen Wang, Xiaosong Bai, Lei Xie, Zhengwei |
| contents | Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consistently underperform in these high-complexity scenarios. Here we present MolClaw, an autonomous agent that leads drug molecule evaluation, screening, and optimization. It unifies over 30 specialized domain resources through a three-tier hierarchical skill architecture (70 skills in total) that facilitates agent long-term interaction at runtime: tool-level skills standardize atomic operations, workflow-level skills compose them into validated pipelines with quality check and reflection, and a discipline-level skill supplies scientific principles governing planning and verification across all scenarios in the field. Additionally, we introduce MolBench, a benchmark comprising molecular screening, optimization, and end-to-end discovery challenges spanning 8 to 50+ sequential tool calls. MolClaw achieves state-of-the-art performance across all metrics, and ablation studies confirm that gains concentrate on tasks that demand structured workflows while vanishing on those solvable with ad hoc scripting, establishing workflow orchestration competence as the primary capability bottleneck for AI-driven drug discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21937 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization Zhang, Lisheng Wang, Lilong Sun, Xiangyu Tang, Wei Su, Haoyang Qian, Yuehui Yang, Qikui Li, Qingsong Tang, Zhenyu Sun, Haoran Han, Yingnan Jiang, Yankai Lou, Wenjie Zhou, Bowen Wang, Xiaosong Bai, Lei Xie, Zhengwei Artificial Intelligence Multiagent Systems Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consistently underperform in these high-complexity scenarios. Here we present MolClaw, an autonomous agent that leads drug molecule evaluation, screening, and optimization. It unifies over 30 specialized domain resources through a three-tier hierarchical skill architecture (70 skills in total) that facilitates agent long-term interaction at runtime: tool-level skills standardize atomic operations, workflow-level skills compose them into validated pipelines with quality check and reflection, and a discipline-level skill supplies scientific principles governing planning and verification across all scenarios in the field. Additionally, we introduce MolBench, a benchmark comprising molecular screening, optimization, and end-to-end discovery challenges spanning 8 to 50+ sequential tool calls. MolClaw achieves state-of-the-art performance across all metrics, and ablation studies confirm that gains concentrate on tasks that demand structured workflows while vanishing on those solvable with ad hoc scripting, establishing workflow orchestration competence as the primary capability bottleneck for AI-driven drug discovery. |
| title | MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2604.21937 |