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.
@article{arxiv.2509.19931,
title = {Documentation Retrieval Improves Planning Language Generation},
author = {Renxiang Wang and Li Zhang},
journal= {arXiv preprint arXiv:2509.19931},
year = {2025}
}