# Improved Generalized Planning with LLMs through Strategy Refinement and Reflection

arXiv: https://arxiv.org/abs/2508.13876 · HTML: https://mlsanity.com/paper/2508.13876/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks](https://mlsanity.com/paper/2402.08115/) (2024)
- [Code Repair with LLMs gives an Exploration-Exploitation Tradeoff](https://mlsanity.com/paper/2405.17503/) (2024)
- [Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning](https://mlsanity.com/paper/2311.09830/) (2023)

## Built on by (most cited first, 7 of 7)

- [What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering](https://mlsanity.com/paper/2601.20164/) (2026)
- [Language Models as Higher-Order Planning Formalizers](https://mlsanity.com/paper/2603.23844/) (2026)
- [Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents](https://mlsanity.com/paper/2605.06957/) (2026)
- [LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning](https://mlsanity.com/paper/2605.29649/) (2026)
- [Provably Complete Generalized Planning with LLMs](https://mlsanity.com/paper/2609.27105/) (2026)
- [LLM-Evolved Pattern Generators for Optimal Classical Planning](https://mlsanity.com/paper/2606.02438/) (2026)
- [Generating Instance Generators in PDDL Planning](https://mlsanity.com/paper/2609.06071/) (2026)

## Abstract (arXiv)

LLMs have recently been used to generate Python programs representing generalized plans in PDDL planning, i.e., plans that generalize across the tasks of a given PDDL domain. Previous work proposed a framework consisting of three steps: the LLM first generates a summary and then a strategy for the domain, both in natural language, and then implements that strategy as a Python program, that gets debugged on example planning tasks. In that work, only one strategy is generated and passed directly to the program generation. If the strategy is incorrect, its implementation will therefore result in an incorrect generalized plan. Here, we introduce an approach that generates the strategy in the form of pseudocode and enables automatic debugging of the pseudocode, hence allowing us to identify and fix errors prior to the generation of the generalized plan itself. Additionally, we extend the Python debugging phase with a reflection step prompting the LLM to pinpoint the reason for the observed plan failure. Finally, we take inspiration from LLM code generation to produce several program variants and pick the best one. Running experiments on 17 benchmark domains with two reasoning and two non-reasoning LLMs, we show that these extensions substantially improve the quality of the generalized plans. Our best performing configuration achieves an average coverage of 82% across the domains.