SEISMO: Increasing Sample Efficiency in Molecular Optimization with a Trajectory-Aware LLM Agent

TL;DR

SEISMO is a novel LLM-based agent that significantly improves sample efficiency in molecular optimization by leveraging trajectory-aware prompts and explanatory feedback, outperforming prior methods across multiple benchmarks.

Contribution

Introduces SEISMO, an online LLM agent that updates after each oracle call, utilizing full trajectory context and structured feedback for more efficient molecular optimization.

Findings

SEISMO achieves 2-3x higher optimization efficiency than prior methods.

Reaches near-optimal scores within 50 oracle calls in benchmark tasks.

Providing explanatory feedback further enhances optimization efficiency.

Abstract

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.