# Mozi: Governed Autonomy for Drug Discovery LLM Agents

arXiv: https://arxiv.org/abs/2603.03655 · HTML: https://mlsanity.com/paper/2603.03655/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 33 of its 89 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 33)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Structure-based Drug Design with Equivariant Diffusion Models](https://mlsanity.com/paper/2210.13695/) (2022)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets](https://mlsanity.com/paper/2205.07249/) (2022)
- [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://mlsanity.com/paper/2303.03543/) (2023)
- [DeepDTA: Deep Drug-Target Binding Affinity Prediction](https://mlsanity.com/paper/1801.10193/) (2018)
- [MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling](https://mlsanity.com/paper/2511.11793/) (2025)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [CRISPR-GPT for Agentic Automation of Gene-editing Experiments](https://mlsanity.com/paper/2404.18021/) (2024)
- [DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration](https://mlsanity.com/paper/2411.15692/) (2024)
- [LIDDIA: Language-based Intelligent Drug Discovery Agent](https://mlsanity.com/paper/2502.13959/) (2025)
- [PharmAgents: Building a Virtual Pharma with Large Language Model Agents](https://mlsanity.com/paper/2503.22164/) (2025)
- [A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding](https://mlsanity.com/paper/2406.05540/) (2024)
- [DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery](https://mlsanity.com/paper/2505.13940/) (2025)
- [RAG-Enhanced Collaborative LLM Agents for Drug Discovery](https://mlsanity.com/paper/2502.17506/) (2025)
- [Multi-domain Distribution Learning for De Novo Drug Design](https://mlsanity.com/paper/2508.17815/) (2025)
- [LLM Agent Swarm for Hypothesis-Driven Drug Discovery](https://mlsanity.com/paper/2504.17967/) (2025)
- [Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale](https://mlsanity.com/paper/2512.20469/) (2025)
- [K-Dense Analyst: Towards Fully Automated Scientific Analysis](https://mlsanity.com/paper/2508.07043/) (2025)
- [Exploring Modularity of Agentic Systems for Drug Discovery](https://mlsanity.com/paper/2506.22189/) (2025)

## Built on by (most cited first, 5 of 5)

- [MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization](https://mlsanity.com/paper/2604.21937/) (2026)
- [StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery](https://mlsanity.com/paper/2606.11851/) (2026)
- [ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams](https://mlsanity.com/paper/2604.15994/) (2026)
- [Evaluating Agentic Bioinformatics through Function, Evidence, and Validation](https://mlsanity.com/paper/2607.27556/) (2026)
- [From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?](https://mlsanity.com/paper/2610.06411/) (2026)

## Abstract (arXiv)

Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist.