# Iterative Formalization and Planning in Partially Observable Environments

arXiv: https://arxiv.org/abs/2505.13126 · HTML: https://mlsanity.com/paper/2505.13126/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 74 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation](https://mlsanity.com/paper/2208.08227/) (2022)
- [WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment](https://mlsanity.com/paper/2402.12275/) (2024)
- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [Counting to Explore and Generalize in Text-based Games](https://mlsanity.com/paper/1806.11525/) (2018)
- [Learning adaptive planning representations with natural language guidance](https://mlsanity.com/paper/2312.08566/) (2023)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [Goal-Oriented Script Construction](https://mlsanity.com/paper/2107.13189/) (2021)
- [Analogous Process Structure Induction for Sub-event Sequence Prediction](https://mlsanity.com/paper/2010.08525/) (2020)
- [Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning](https://mlsanity.com/paper/2311.09830/) (2023)
- [ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games](https://mlsanity.com/paper/2305.14879/) (2023)
- [On the Limit of Language Models as Planning Formalizers](https://mlsanity.com/paper/2412.09879/) (2024)
- [PDDLEGO: Iterative Planning in Textual Environments](https://mlsanity.com/paper/2405.19793/) (2024)
- [LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions](https://mlsanity.com/paper/2501.00830/) (2025)
- [Statically Contextualizing Large Language Models with Typed Holes](https://mlsanity.com/paper/2409.00921/) (2024)
- [Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization](https://mlsanity.com/paper/2311.09510/) (2023)

## Built on by (most cited first, 1 of 1)

- [KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning](https://mlsanity.com/paper/2602.04129/) (2026)

## Abstract (arXiv)

Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve performance and control. While most existing methodology only applies to fully observable environments, we adapt to the more realistic and challenging partially observable environments without sufficient information to make a complete plan. We propose PDDLego, a framework to iteratively formalize, plan, grow, and refine PDDL representations by decomposing the environment and the goal into fully observable episodes. Without finetuning, in-context exemplars, or trajectories, PDDLego improves planning success and exhibits robustness against problem complexity compared to end-to-end approaches. We also show that the domain knowledge captured after a successful trial can benefit future tasks.