让大模型生成高层次规划代码，解决复杂问题时传统方法失效的问题。
Language Models as Higher-Order Planning Formalizers
- 用大模型生成高层程序，自动展开成大规模规划描述
- 在复杂任务中比传统直接转PDDL的方法性能提升显著
- 适合需要处理高复杂度规划的智能系统研究者
近期研究表明，即使经过推理链训练的大语言模型，在面对复杂规划问题时也会迅速失效。现有‘大模型作为形式化工具’的方法通过将自然语言描述转化为PDDL等结构化表示，再交由程序化求解器处理。但我们发现该方法的成功可能被夸大——标准测试集中的问题常存在自然语言到PDDL的一一对应关系，不符合真实场景。为此，我们提出‘解缠问题’：一个简洁的自然语言描述可映射为极庞大的PDDL表达。在四个标准规划领域上使用解缠变体进行实验，发现现有形式化方法仍无法有效扩展。为此我们提出新范式：‘大模型作为高阶形式化器’，即让大模型生成捕捉重复逻辑的高层程序，再动态生成对应的大型PDDL。该方法将输出令牌数与底层形式化及搜索空间的组合爆炸解耦，显著提升了复杂问题下的表现。
原文摘要 · Abstract (English)
Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems become more complex. LLM-as-Formalizers aim to address this by employing LLMs as a bridge to translate natural language descriptions into structured planning representations such as PDDL, which are then fed to a programmatic solver. We observe that its success may be overstated because planning problem descriptions in standard benchmarks often have a one-to-one mapping to PDDL, which departs from real use cases. To address this, we introduce the notion of unraveling problems where a natural yet succinct description translates into a very large PDDL representation. Using unraveling variants of four standard planning domains, we demonstrate that LLM Formalizers also do not always scale. We tackle this challenge by introducing a new paradigm, LLM-as-Higher-Order-Formalizer, where the LLM generates a high-level program that captures the recurrent logic within the description and in turn generates the larger PDDL representation. This decouples token output from the combinatorial explosion of the underlying formalization and search space, leading to improved performance for complex problems.
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。