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

arXiv: https://arxiv.org/abs/2606.29700 · HTML: https://mlsanity.com/paper/2606.29700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 14 of 14)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [ACPBench: Reasoning about Action, Change, and Planning](https://mlsanity.com/paper/2410.05669/) (2024)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions](https://mlsanity.com/paper/2405.04215/) (2024)
- [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://mlsanity.com/paper/2407.12979/) (2024)
- [Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts](https://mlsanity.com/paper/2409.15915/) (2024)
- [Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning](https://mlsanity.com/paper/2406.10479/) (2024)
- [On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL](https://mlsanity.com/paper/2601.14456/) (2026)

## Abstract (arXiv)

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 planner-in-the-loop framework that uses validator and planner diagnostics to revise non-executable specifications through localized edits. Building on this infrastructure, we develop a planner-grounded optimization recipe that combines parameter-efficient Low-Rank Adaptation supervised fine-tuning, offline planner-derived preference pairs for Direct Preference Optimization, and inference-time planner-in-the-loop repair, without requiring online planner calls during training. We also provide a unified evaluation suite for parseability, solvability, specification similarity, and outcome-aware plan-level consistency against planner references. Experiments on representative model families show substantial gains in planner success and plan-level agreement, with improved robustness under difficulty scaling and cross-domain variation. These results highlight the value of externally verifiable formalization for reliable deployment of LLMs in safety- or security-sensitive planning systems. Code and data are available at: https://github.com/ibasicplan/NL-PDDL-Bench