# On the Limit of Language Models as Planning Formalizers

arXiv: https://arxiv.org/abs/2412.09879 · HTML: https://mlsanity.com/paper/2412.09879/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [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)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (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)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [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)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [Learning adaptive planning representations with natural language guidance](https://mlsanity.com/paper/2312.08566/) (2023)
- [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)
- [Causal Reasoning of Entities and Events in Procedural Texts](https://mlsanity.com/paper/2301.10896/) (2023)
- [PROC2PDDL: Open-Domain Planning Representations from Texts](https://mlsanity.com/paper/2403.00092/) (2024)
- [PDDLEGO: Iterative Planning in Textual Environments](https://mlsanity.com/paper/2405.19793/) (2024)
- [Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications](https://mlsanity.com/paper/2309.05542/) (2023)
- [OpenPI2.0: An Improved Dataset for Entity Tracking in Texts](https://mlsanity.com/paper/2305.14603/) (2023)
- [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, 18 of 18)

- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [Towards a Common Framework for Autoformalization](https://mlsanity.com/paper/2509.09810/) (2025)
- [ESCA: Contextualizing Embodied Agents via Scene-Graph Generation](https://mlsanity.com/paper/2510.15963/) (2025)
- [Theory-Scale Auto-Formalization of Logics for Computer Science](https://mlsanity.com/paper/2606.26525/) (2026)
- [Unifying Inference-Time Planning Language Generation](https://mlsanity.com/paper/2505.14763/) (2025)
- [Vision Language Models Cannot Plan, but Can They Formalize?](https://mlsanity.com/paper/2509.21576/) (2025)
- [Language Model as Planner and Formalizer under Constraints](https://mlsanity.com/paper/2510.05486/) (2025)
- [Iterative Formalization and Planning in Partially Observable Environments](https://mlsanity.com/paper/2505.13126/) (2025)
- [A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems](https://mlsanity.com/paper/2505.13252/) (2025)
- [Language Models as Higher-Order Planning Formalizers](https://mlsanity.com/paper/2603.23844/) (2026)
- [Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding](https://mlsanity.com/paper/2605.09271/) (2026)
- [Grounded Vision-Language Interpreter for Long-Horizon Bimanual Task and Motion Planning](https://mlsanity.com/paper/2506.03270/) (2025)
- [Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents](https://mlsanity.com/paper/2604.27699/) (2026)
- [Robust Asynchronous Planning via Auto-Formalization](https://mlsanity.com/paper/2606.00981/) (2026)
- [A Neurosymbolic Approach for Constructing Planning Domain Models from Clinical Narratives](https://mlsanity.com/paper/2608.21186/) (2026)
- [From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning](https://mlsanity.com/paper/2608.21897/) (2026)
- [Grounded Evaluation and Repair for NL-to-PDDL Problem Generation](https://mlsanity.com/paper/2609.09898/) (2026)
- [CVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language Models](https://mlsanity.com/paper/2610.03383/) (2026)

## Abstract (arXiv)

Large Language Models have been found to create plans that are neither executable nor verifiable in grounded environments. An emerging line of work demonstrates success in using the LLM as a formalizer to generate a formal representation of the planning domain in some language, such as Planning Domain Definition Language (PDDL). This formal representation can be deterministically solved to find a plan. We systematically evaluate this methodology while bridging some major gaps. While previous work only generates a partial PDDL representation, given templated, and therefore unrealistic environment descriptions, we generate the complete representation given descriptions of various naturalness levels. Among an array of observations critical to improve LLMs' formal planning abilities, we note that most large enough models can effectively formalize descriptions as PDDL, outperforming those directly generating plans, while being robust to lexical perturbation. As the descriptions become more natural-sounding, we observe a decrease in performance and provide detailed error analysis.