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.

翻译：生成满足多个物理化学性质精确数值约束的分子至关重要且具有挑战性。尽管大语言模型（LLMs）具有强大的表达能力，但在缺乏外部结构和反馈的情况下，它们难以实现精确的多目标控制和数值推理。我们提出了 \textbf{M^4olGen}，一个用于多属性约束下分子生成的片段级、检索增强的两阶段框架。第一阶段：原型生成：一个多智能体推理器执行检索锚定的片段级编辑，以生成接近可行区域的候选分子。第二阶段：基于强化学习的细粒度优化：一个使用组相对策略优化（GRPO）训练的片段级优化器，应用单跳或多跳优化，以显式最小化属性误差至目标值，同时调控编辑复杂度和与原型的偏差。一个大规模、自动构建的、包含片段编辑推理链和测量属性变化的数据集支撑着这两个阶段，实现了确定性的、可复现的监督以及可控的多跳推理。与先前工作不同，我们的框架通过利用片段更好地对分子进行推理，并支持向数值目标的可控优化。在两组属性约束（QED、LogP、分子量以及HOMO、LUMO）下的生成实验表明，我们的方法在多属性目标的分子有效性和精确满足度方面持续取得提升，优于强大的LLMs和基于图的算法。