Unifying Inference-Time Planning Language Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912632907235328 |
|---|---|
| author | Kagitha, Prabhu Prakash Sun, Bo Desai, Ishan Zhu, Andrew Huang, Cassie Li, Manling Li, Ziyang Zhang, Li |
| author_facet | Kagitha, Prabhu Prakash Sun, Bo Desai, Ishan Zhu, Andrew Huang, Cassie Li, Manling Li, Ziyang Zhang, Li |
| contents | A line of work in planning uses LLM not to generate a plan, but to generate a formal representation in some planning language, which can be input into a symbolic solver to deterministically find a plan. While showing improved trust and promising performance, dozens of recent publications have proposed scattered methods on a variety of benchmarks under different experimental settings. We attempt to unify the inference-time LLM-as-formalizer methodology for classical planning by proposing a unifying framework based on intermediate representations. We thus systematically evaluate more than a dozen pipelines that subsume most existing work, while proposing novel ones that involve syntactically similar but high resource intermediate languages (such as a Python wrapper of PDDL). We provide recipes for planning language generation pipelines, draw a series of conclusions showing the efficacy of their various components, and evidence their robustness against problem complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14763 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unifying Inference-Time Planning Language Generation Kagitha, Prabhu Prakash Sun, Bo Desai, Ishan Zhu, Andrew Huang, Cassie Li, Manling Li, Ziyang Zhang, Li Computation and Language A line of work in planning uses LLM not to generate a plan, but to generate a formal representation in some planning language, which can be input into a symbolic solver to deterministically find a plan. While showing improved trust and promising performance, dozens of recent publications have proposed scattered methods on a variety of benchmarks under different experimental settings. We attempt to unify the inference-time LLM-as-formalizer methodology for classical planning by proposing a unifying framework based on intermediate representations. We thus systematically evaluate more than a dozen pipelines that subsume most existing work, while proposing novel ones that involve syntactically similar but high resource intermediate languages (such as a Python wrapper of PDDL). We provide recipes for planning language generation pipelines, draw a series of conclusions showing the efficacy of their various components, and evidence their robustness against problem complexity. |
| title | Unifying Inference-Time Planning Language Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.14763 |