用分层验证强化学习，让模型自动设计可验证的基因回路。
GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design
- 分五层奖励机制，从代码执行到功能拓扑逐步验证正确性。
- 相比二元奖励，功能推理任务成功率提升14至16个百分点。
- 适合合成生物学、AI辅助设计与可验证系统研发人员。
尽管合成生物学发展数十年，基因回路设计仍依赖人工且高度专业化。本文将问题转化为代码生成：模型输出pysbol3代码以构建符合合成生物学开放语言（SBOL）的基因回路，该格式支持自动化验证。提出GenCircuit-RL框架，采用分层验证奖励机制，将正确性分解为五个层级——从代码执行到任务特定拓扑检查，并引入四阶段课程学习，逐步转移优化重点从代码生成转向功能推理。同时构建SynBio-Reason基准，包含4,753个回路，涵盖六种典型类型和九类任务，包括代码修复与从零设计，提供未见过的生物元件用于分布外评估。分层验证使功能推理任务成功率比二元奖励提升14至16个百分点，课程学习对高性能设计至关重要。模型生成拓扑正确的回路，能泛化至新生物元件，并复现文献中的经典设计。
原文摘要 · Abstract (English)
Genetic circuit design remains a laborious, expert-driven process despite decades of progress in synthetic biology. We study this problem through code generation: models produce Python code in pysbol3 to construct genetic circuits in the Synthetic Biology Open Language (SBOL), a formal representation that supports automated verification. We introduce GenCircuit-RL, a reinforcement learning framework built around hierarchical verification rewards that decompose correctness into five levels, from code execution to task-specific topological checks, and a four-stage curriculum that shifts optimization pressure from code generation to functional reasoning. We also introduce SynBio-Reason, a benchmark of 4,753 circuits spanning six canonical circuit types and nine tasks from code repair to de novo design, with held-out biological parts for out-of-distribution evaluation. Hierarchical verification improves task success on functional reasoning tasks by 14 to 16 percentage points over binary rewards, and curriculum learning is required for strong design performance. The resulting models generate topologically correct circuits, generalize to novel biological parts, and rediscover canonical designs from the synthetic biology literature.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。