# M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization

arXiv: https://arxiv.org/abs/2609.34491 · HTML: https://mlsanity.com/paper/2609.34491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 22 of 22)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Optimization of Molecules via Deep Reinforcement Learning](https://mlsanity.com/paper/1810.08678/) (2018)
- [LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset](https://mlsanity.com/paper/2402.09391/) (2024)
- [ChemLLM: A Chemical Large Language Model](https://mlsanity.com/paper/2402.06852/) (2024)
- [ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations](https://mlsanity.com/paper/1908.01425/) (2019)
- [Efficient Evolutionary Search Over Chemical Space with Large Language Models](https://mlsanity.com/paper/2406.16976/) (2024)
- [DrugAssist: A Large Language Model for Molecule Optimization](https://mlsanity.com/paper/2401.10334/) (2023)
- [De Novo Molecular Generation via Connection-aware Motif Mining](https://mlsanity.com/paper/2302.01129/) (2023)
- [PharmAgents: Building a Virtual Pharma with Large Language Model Agents](https://mlsanity.com/paper/2503.22164/) (2025)
- [DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery](https://mlsanity.com/paper/2505.13940/) (2025)
- [GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization](https://mlsanity.com/paper/2502.13398/) (2025)
- [MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization](https://mlsanity.com/paper/2505.20820/) (2025)
- [A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization](https://mlsanity.com/paper/2505.16094/) (2025)
- [TAGMol: Target-Aware Gradient-guided Molecule Generation](https://mlsanity.com/paper/2406.01650/) (2024)
- [Deep Lead Optimization: Leveraging Generative AI for Structural Modification](https://mlsanity.com/paper/2404.19230/) (2024)
- [mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules](https://mlsanity.com/paper/2505.12565/) (2025)
- [Monte-Carlo Graph Search for AlphaZero](https://mlsanity.com/paper/2012.11045/) (2020)
- [Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks](https://mlsanity.com/paper/2411.13280/) (2024)
- [MolX: Enhancing Large Language Models for Molecular Understanding With A Multi-Modal Extension](https://mlsanity.com/paper/2406.06777/) (2024)
- [SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?](https://mlsanity.com/paper/2605.21740/) (2026)

## Abstract (arXiv)

Small-molecule optimization integrates medicinal-chemistry reasoning and computational evidence through iterative, multi-objective decisions. When large language models (LLMs) reason over optimization histories stored primarily in conversational context, they must recover candidate identities, prior evaluations, and task constraints to guide subsequent decisions. We present M3OS, a multi-agent LLM system that decouples molecular-design reasoning from optimization-state management through Monte Carlo graph search. A persistent graph links evaluated candidates, parent-child transformations and evaluation evidence, while rewards and visit statistics guide LLM-assisted parent selection. Two branches combine tool-driven candidate generation with knowledge- and case-guided medicinal-chemistry editing. An execution harness controls graph updates through structured output extraction, molecular validation and task-bound evaluation. Agents receive role-specific contexts, while the graph preserves optimization trajectories beyond their active contexts. Across three molecular optimization benchmarks, M3OS achieves higher success rates than baselines, supporting the integration of persistent search state, specialized agents and controlled execution for multi-constraint optimization.