Agents on a Tree: Pathwise Coordination for Multi-Objective Molecular Optimization

树上的智能体：多目标分子优化的路径协同方法

Abstract: Multi-objective molecular optimization requires searching vast chemical spaces under conflicting objectives, where early design decisions strongly constrain downstream outcomes. Existing methods typically rely on a single policy or fixed scalarization, which limits their ability to represent diverse trade-offs and to explore multiple promising design trajectories.

摘要： 多目标分子优化需要在相互冲突的目标下搜索广阔的化学空间，其中早期的设计决策会极大地限制后续的结果。现有的方法通常依赖于单一策略或固定的标量化方法，这限制了它们表示多样化权衡以及探索多个有前景的设计轨迹的能力。

We propose ATOM, a multi-agent framework that formulates molecular optimization as a tree-structured search. Each node corresponds to an atomic operation and hosts an agent specialized for a particular objective or decision context. Agents coordinate along different paths of the tree rather than enforcing a global consensus, enabling the method to maintain and compare alternative molecular evolution trajectories.

我们提出了 ATOM，这是一个将分子优化建模为树状搜索的多智能体框架。每个节点对应一个原子操作，并托管一个专门针对特定目标或决策环境的智能体。智能体沿着树的不同路径进行协同，而不是强制达成全局共识，这使得该方法能够维护并比较不同的分子演化轨迹。

A global memory of past optimization behaviors further supports balanced exploration and exploitation across objectives. This tree-structured interaction enables reasoning over long-horizon dependencies inherent in molecular design.

全局记忆机制记录了过去的优化行为，进一步支持了跨目标的平衡探索与利用。这种树状交互机制使得模型能够对分子设计中固有的长程依赖关系进行推理。

Experiments on challenging multi-objective benchmarks involving activity, synthesizability, and ADMET-related properties show that ATOM consistently achieves improved Pareto coverage and hypervolume over strong baselines. These results demonstrate the effectiveness of pathwise multi-agent coordination for molecular optimization. Code is available at this link.

在涉及活性、可合成性和 ADMET 相关属性的挑战性多目标基准测试中，实验表明，与强基线方法相比，ATOM 始终能实现更好的帕累托覆盖率（Pareto coverage）和超体积（hypervolume）。这些结果证明了路径式多智能体协同在分子优化中的有效性。代码已在链接中提供。