用大模型进化出更通用的计划生成器，速度快且成本低。
GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
- 用大模型指导进化算法生成可解释的Python计划代码
- 在6个旧+2个新领域平均成功率0.91，接近顶尖水平
- 适合需要快速生成通用规划的自动化系统开发者
我们提出GenePlan（GENeralized Evolutionary Planner），一种利用大语言模型辅助的进化算法框架，用于生成针对经典规划任务（以PDDL描述）的领域相关通用规划器。将通用规划问题转化为优化问题，GenePlan通过迭代演化可解释的Python规划代码，以最小化在多样化问题实例中的计划长度。在六个现有基准领域和两个新领域的实证评估中，GenePlan实现了平均0.91的SAT得分，接近当前最优规划器（0.93），显著优于其他基于LLM的基线方法（如思维链提示，平均SAT得分为0.64）。生成的规划器能快速解决新实例（每任务平均0.49秒），且成本低廉（每个领域平均使用GPT-4o耗资1.82美元）。
原文摘要 · Abstract (English)
We present GenePlan (GENeralized Evolutionary Planner), a novel framework that leverages large language model (LLM) assisted evolutionary algorithms to generate domain-dependent generalized planners for classical planning tasks described in PDDL. By casting generalized planning as an optimization problem, GenePlan iteratively evolves interpretable Python planners that minimize plan length across diverse problem instances. In empirical evaluation across six existing benchmark domains and two new domains, GenePlan achieved an average SAT score of 0.91, closely matching the performance of the state-of-the-art planners (SAT score 0.93), and significantly outperforming other LLM-based baselines such as chain-of-thought (CoT) prompting (average SAT score 0.64). The generated planners solve new instances rapidly (average 0.49 seconds per task) and at low cost (average $1.82 per domain using GPT-4o).
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。