My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents
This paper introduces My Chemical Harness, a route-native evolutionary framework for goal-directed molecular design.
This paper introduces a novel approach to molecular design that combines large language models and deterministic chemistry tools.
Keywords
Before reading this…
Applications
- →molecular discovery
To understand this paper, make sure you know these concepts first:
- large language modelsfind papers →
- deterministic chemistry toolsfind papers →
Abstract
More Like ThisDesigning molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes. We introduce My Chemical Harness, a route-native evolutionary framework for goal-directed molecular design in which the search population consists of executable synthetic pathways rather than isolated molecular graphs. Each route is built from purchasable building blocks and reaction templates, executed by deterministic chemistry tools, and scored through task-specific molecular oracles. Large language models (LLMs) are used only as strategy controllers that select high-level preferences over route length, move type, reaction families, motifs, and exploration pressure, while local code performs route construction, validation, deduplication, scoring, selection, and memory updates. This separation lets the LLM guide exploration without allowing it to introduce hallucinated products or unsupported reaction steps. On a soluble epoxide hydrolase proxy task, our LLM agent improves over single pass LLM and deterministic controllers, reaching state-of-the-art performance across the sEH score, synthetic accessibility score, and AiZynthFinder success rate metrics. These results suggest that constrained LLM agents can play a significant role in molecular discovery without requiring training, fine-tuning, or dedicated generative models.