Optimizing the structure of molecules to achieve desired properties is a central bottleneck across the chemical sciences, particularly in the pharmaceutical industry where it underlies the discovery of new drugs. Since molecular property evaluation often relies on costly and rate-limited oracles, such as experimental assays, molecular optimization must be highly sample-efficient. To address this, we introduce SEISMO, an LLM agent that performs strictly online, inference-time molecular optimization, updating after every oracle call without the need for population-based or batched learning. SEISMO conditions each proposal on the full optimization trajectory, combining natural-language task descriptions with scalar scores and, when available, structured explanatory feedback. Across the Practical Molecular Optimization benchmark of 23 tasks, SEISMO achieves a 2-3 times higher area under the optimisation curve than prior methods, often reaching near-maximal task scores within 50 oracle calls. Our additional medicinal-chemistry tasks show that providing explanatory feedback further improves efficiency, demonstrating that leveraging domain knowledge and structured information is key to sample-efficient molecular optimization.

翻译：优化分子结构以实现目标性质是化学科学领域的一个核心瓶颈，在依赖新药发现的制药行业尤为突出。由于分子性质评估通常依赖于昂贵且速率受限的“预言机”（如实验检测），分子优化必须具备极高的样本效率。为此，我们提出SEISMO——一种严格在线、在推理阶段进行分子优化的大语言模型代理，其在每次预言机调用后即时更新，无需依赖基于种群或批处理的学习机制。SEISMO将每个分子生成提议基于完整的优化轨迹进行条件化，融合了自然语言任务描述、标量评分以及可获取的结构化解释性反馈。在包含23项任务的实用分子优化基准测试中，SEISMO获得的优化曲线下面积较现有方法高出2-3倍，且通常在50次预言机调用内即可接近任务最高分。我们在额外药物化学任务上的实验表明，提供解释性反馈能进一步提升优化效率，这证明利用领域知识与结构化信息是实现样本高效分子优化的关键。