用语言模型生成可验证的程序化规划策略，解决复杂PDDL问题
Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
- 将PDDL问题转化为Python程序作为通用规划策略
- 在限定资源下解决比传统规划器和现有语言模型更多问题
- 首次实现无需外部验证的可证明正确性，适合复杂规划任务
我们研究语言模型（LMs）在基于规划领域定义语言（PDDL）的世界模型上的规划应用。通过提示语言模型生成用于求解特定领域PDDL问题的Python程序，构建通用策略。值得注意的是，该方法合成的策略相对于给定的PDDL领域是可证明正确的，且不依赖外部验证器。我们在竞赛基准上进行实验，结果表明，在固定时间和内存约束下，我们的策略能解决比传统PDDL规划器及近期语言模型方法更多的问题。该方法实现了名为LMPlan的规划器，可处理包含数百个相关对象的规划问题。令人意外的是，当将自然语言替换为无意义符号（如将 (at dog kitchen) 重写为 (p2 o1 o3)）时，语言模型仍能有效规划，这挑战了语言模型依赖语义理解或记忆训练数据中解法的传统假设，值得进一步探索。
原文摘要 · Abstract (English)
We study the usage of language models (LMs) for planning over world models specified in the Planning Domain Definition Language (PDDL). We prompt LMs to generate Python programs that serve as generalised policies for solving PDDL problems from a given domain. Notably, our approach synthesises policies that are provably sound relative to the PDDL domain without reliance on external verifiers. We conduct experiments on competition benchmarks which show that our policies can solve more PDDL problems than PDDL planners and recent LM approaches within a fixed time and memory constraint. Our approach manifests in the LMPlan planner which can solve planning problems with several hundreds of relevant objects. Surprisingly, we observe that LMs used in our framework sometimes plan more effectively over PDDL problems written in meaningless symbols in place of natural language; e.g. rewriting (at dog kitchen) as (p2 o1 o3). This finding challenges hypotheses that LMs reason over word semantics and memorise solutions from its training corpus, and is worth further exploration.
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。