# MFG: Multi-turn Feedback Guided Molecular Optimization

arXiv: https://arxiv.org/abs/2610.18851 · HTML: https://mlsanity.com/paper/2610.18851/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 8 of 8)

- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset](https://mlsanity.com/paper/2402.09391/) (2024)
- [DrugAssist: A Large Language Model for Molecule Optimization](https://mlsanity.com/paper/2401.10334/) (2023)
- [MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization](https://mlsanity.com/paper/2010.02318/) (2020)
- [A Deep Generative Model for Molecule Optimization via One Fragment Modification](https://mlsanity.com/paper/2012.04231/) (2020)
- [ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback](https://mlsanity.com/paper/2305.18090/) (2023)
- [DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization](https://mlsanity.com/paper/2502.07237/) (2025)
- [Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning](https://mlsanity.com/paper/2603.05900/) (2026)

## Abstract (arXiv)

Multi-objective molecular optimization is a critical process in drug discovery that aims to modify a given molecule to simultaneously improve multiple properties while maintaining a similar overall structure. This process often requires iterative modifications guided by computational or experimental feedback. Recent large language model (LLM)-based methods have begun to explore this iterative approach; however, these methods are not explicitly trained to leverage such feedback, while existing approaches primarily focus on single-turn molecular optimization. To address this gap, we introduce Multi-turn Feedback Guided (MFG) molecular optimization, a reinforcement learning framework that trains an LLM to progressively optimize molecules using feedback from previous turns. MFG introduces a feedback vector capturing both property improvements and source molecule similarity, alongside a feedback-aligned reward function that promotes progressive improvement across turns. We apply MFG over GeLLM3O, a state-of-the-art LLM model for multi-objective molecular optimization, evaluate GeLLM3O-MFG on ten multi-objective molecular optimization tasks. The results demonstrate that GeLLM3O-MFG achieves the highest average similarity-constrained success rate (81.50%), outperforming the base model GeLLM3O (70.81%).