Skip to content
Search
paperJune 2026Unreviewed

Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop Feedback

Jiamei Jiang, Jiajing Zhang, Feifei Mo, Linjing Li, Daniel Zeng

View resourcePDF

Abstract

Planning often requires symbolic specifications that are both executable and verifiable. For large language models deployed in autonomous or decision-support systems, failures in such formalization may lead to unverifiable decisions, execution failures, or unsafe downstream behavior. We present NL-PDDL-Bench, a multi-domain benchmark for natural-language-to-PDDL specification construction with planner-verified executability and controlled difficulty scaling by object count. We further propose a

Categories

Benchmarks & Evaluation

Cite

@misc{jiang2026secure,
  title = {{Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop Feedback}},
  author = {Jiamei Jiang and Jiajing Zhang and Feifei Mo and Linjing Li and Daniel Zeng},
  year = {2026},
  month = jun,
  eprint = {2606.29700},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.29700}
}