Newest papers

MFG: Multi-turn Feedback Guided Molecular Optimization

Trieu Nguyen, Frazier N. Baker, Ruoxi Gao, Daniel Adu‐Ampratwum, Xia Ning · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.18851 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La optimización molecular multi-objetivo es un proceso crítico en el descubrimiento de fármacos que tiene como objetivo modificar una molécula dada para mejorar simultáneamente múltiples propiedades mientras se mantiene una estructura general similar. Este proceso a menudo requiere modificaciones iterativas guiadas por la retroalimentación computacional o experimental. Los métodos recientes basados en el modelo de gran lenguaje (LLM) han comenzado a explorar este enfoque iterativo; sin embargo, estos métodos no están explicitamente entrenados para aprovechar tales retroalimentaciones, mientras que los enfoques existentes se centran principalmente en la optimización molecular de única vuelta. Para abordar esta brecha, introducimos la optimización molecular Multi-turn Feedback Guided (MFG), un marco de aprendizaje reforzado que capacita a un LLM

Machine translation (Meta M2M100); the English original follows.

Abstract

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 $\text{GeLLM}^{3}\text{O}$, a state-of-the-art LLM model for multi-objective molecular optimization, evaluate $\text{GeLLM}^{3}\text{O-MFG}$ on ten multi-objective molecular optimization tasks. The results demonstrate that $\text{GeLLM}^{3}\text{O-MFG}$ achieves the highest average similarity-constrained success rate ($81.50%$), outperforming the base model $\text{GeLLM}^{3}\text{O}$ ($70.81%$).

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Leverage (statistics), Process (computing), Reinforcement learning, Iterative and incremental development, Property (philosophy)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange