M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints

TL;DR

M^4olGen is a two-stage, retrieval-augmented framework for molecule generation that precisely satisfies multiple property constraints through fragment-level reasoning and reinforcement learning optimization.

Contribution

It introduces a novel multi-agent, multi-stage approach with a curated dataset, improving multi-property molecule generation over prior methods.

Findings

Outperforms existing models in validity and property satisfaction.

Supports controllable, multi-hop fragment reasoning.

Demonstrates effectiveness on multiple physicochemical property constraints.

Abstract

Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce \textbf{M olGen}, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.