Documentation Retrieval Improves Planning Language Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918150355812352 |
|---|---|
| author | Wang, Renxiang Zhang, Li |
| author_facet | Wang, Renxiang Zhang, Li |
| contents | Certain strong LLMs have shown promise for zero-shot formal planning by generating planning languages like PDDL. Yet, the performance of most open-source models under 50B parameters has been reported to be close to zero due to the low-resource nature of these languages. We significantly improve their performance via a series of lightweight pipelines that integrates documentation retrieval with modular code generation and error refinement. With models like Llama-4-Maverick, our best pipeline improves plan correctness from 0% to over 80% on the common BlocksWorld domain. However, while syntactic errors are substantially reduced, semantic errors persist in more challenging domains, revealing fundamental limitations in current models' reasoning capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19931 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Documentation Retrieval Improves Planning Language Generation Wang, Renxiang Zhang, Li Information Retrieval F.2.2; I.2.7 Certain strong LLMs have shown promise for zero-shot formal planning by generating planning languages like PDDL. Yet, the performance of most open-source models under 50B parameters has been reported to be close to zero due to the low-resource nature of these languages. We significantly improve their performance via a series of lightweight pipelines that integrates documentation retrieval with modular code generation and error refinement. With models like Llama-4-Maverick, our best pipeline improves plan correctness from 0% to over 80% on the common BlocksWorld domain. However, while syntactic errors are substantially reduced, semantic errors persist in more challenging domains, revealing fundamental limitations in current models' reasoning capabilities. |
| title | Documentation Retrieval Improves Planning Language Generation |
| topic | Information Retrieval F.2.2; I.2.7 |
| url | https://arxiv.org/abs/2509.19931 |