# MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization

arXiv: https://arxiv.org/abs/2604.21937 · HTML: https://mlsanity.com/paper/2604.21937/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 68 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools](https://mlsanity.com/paper/2503.10970/) (2025)
- [Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations](https://mlsanity.com/paper/2505.21318/) (2025)
- [DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration](https://mlsanity.com/paper/2411.15692/) (2024)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [LIDDIA: Language-based Intelligent Drug Discovery Agent](https://mlsanity.com/paper/2502.13959/) (2025)
- [Activity Cliff Prediction: Dataset and Benchmark](https://mlsanity.com/paper/2302.07541/) (2023)
- [SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents](https://mlsanity.com/paper/2512.24189/) (2025)
- [Mozi: Governed Autonomy for Drug Discovery LLM Agents](https://mlsanity.com/paper/2603.03655/) (2026)

## Built on by (most cited first, 7 of 7)

- [Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent](https://mlsanity.com/paper/2606.30616/) (2026)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)
- [SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation](https://mlsanity.com/paper/2608.02287/) (2026)
- [CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows](https://mlsanity.com/paper/2608.06961/) (2026)
- [Evaluating Agentic Harness Systems for Autonomous Computational Pathology](https://mlsanity.com/paper/2607.02598/) (2026)
- [Evaluating Agentic Bioinformatics through Function, Evidence, and Validation](https://mlsanity.com/paper/2607.27556/) (2026)
- [Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment](https://mlsanity.com/paper/2608.21057/) (2026)

## Abstract (arXiv)

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.