用提示词控制合成路径生成，一次模型搞定多种约束。
Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning
- 将目标分子和约束条件统一成提示词，用单个解码器生成路径。
- 在深度与起始物料约束下，准确率提升13.7和31.2点。
- 生成速度比传统方法快数十倍，适合快速试错场景。
逆合成规划旨在通过多步反应将目标分子连接到可购起始原料。经典规划器通过迭代应用单步反应模型进行搜索，受限版本常需专用算法或架构改动。直接路径生成将逆合成重定义为序列生成，但现有方法仍需为不同规划需求训练独立模型。我们提出Ariadne，一个仅使用解码器的路径生成器，将目标分子、可选约束和路径整合为一个提示-补全序列。在RetroCast/PaRoutes mkt-cnv-160基准集上，一个24层检查点在路径深度和必需起始物提示下，分别使Solv-0提升13.7和31.2点。Ariadne在必需起始物的Top-10和Solv-0指标上优于双向搜索规划器DESP，仅需24 GPU分钟，而DESP需6.8 GPU小时。在标准重建任务中，Ariadne性能接近DMS Explorer XL，但推理时间约为其一半。在额外的仅目标基准测试中，Ariadne在路径保留重建上表现最佳，而AiZynthFinder MCTS在多个Solv-0比较中仍更优。这些结果将序列生成从专用逆合成模型扩展至提示条件下的结构化路径生成。我们开源代码与训练脚本以支持后续研究，但未引入一级至三级路径验证器；这些仍是模型对实验化学家有用前的主要瓶颈。
原文摘要 · Abstract (English)
Retrosynthetic planning seeks to connect a target molecule to commercially available starting materials through a multistep route. Classical planners construct such routes by iteratively applying single-step reaction models within a search procedure; constrained variants often require specialized algorithms or architectural changes. Direct route generation reframes retrosynthesis as sequence generation, but existing direct-generation methods still train separate models for different planning specifications. We introduce Ariadne, a decoder-only route generator that represents the target, optional constraints, and route in one prompt-completion sequence. On the RetroCast/PaRoutes mkt-cnv-160 benchmark family, one 24-layer checkpoint follows route-depth and required-starting-material prompts: adding the corresponding prompt fields raises Solv-0 by 13.7 points for depth constraints and 31.2 points for required-leaf constraints. Ariadne also improves over DESP, a bidirectional search planner, on required-leaf Top-10 and Solv-0 in 24 GPU-minutes versus 6.8 GPU-hours. On standard reconstruction, Ariadne is comparable to DMS Explorer XL at about half the reported inference time. Across additional target-only benchmarks, Ariadne's clearest gains are on route-holdout reconstruction, whereas AiZynthFinder MCTS remains stronger on several Solv-0 comparisons. These results extend sequence generation from specialist retrosynthesis models to prompt-conditioned structural route generation. We release the codebase and training scripts to support further work, but do not introduce Tier-1--3 route checkers; those remain the main bottleneck before models of this kind can become useful to experimental chemists.
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。