# PROC2PDDL: Open-Domain Planning Representations from Texts

arXiv: https://arxiv.org/abs/2403.00092 · HTML: https://mlsanity.com/paper/2403.00092/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks](https://mlsanity.com/paper/2205.05718/) (2022)
- [Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs](https://mlsanity.com/paper/2308.09895/) (2023)
- [Learning adaptive planning representations with natural language guidance](https://mlsanity.com/paper/2312.08566/) (2023)
- [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, 15 of 15)

- [Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo](https://mlsanity.com/paper/2504.13139/) (2025)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [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)
- [CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans](https://mlsanity.com/paper/2406.15823/) (2024)
- [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)
- [Language Model as Planner and Formalizer under Constraints](https://mlsanity.com/paper/2510.05486/) (2025)
- [Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism](https://mlsanity.com/paper/2603.03784/) (2026)
- [Language Models as Higher-Order Planning Formalizers](https://mlsanity.com/paper/2603.23844/) (2026)
- [GinSign: Grounding Natural Language Into System Signatures for Temporal Logic Translation](https://mlsanity.com/paper/2512.16770/) (2025)
- [Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents](https://mlsanity.com/paper/2606.21740/) (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)

## Abstract (arXiv)

Planning in a text-based environment continues to be a major challenge for AI systems. Recent approaches have used language models to predict a planning domain definition (e.g., PDDL) but have only been evaluated in closed-domain simulated environments. To address this, we present Proc2PDDL , the first dataset containing open-domain procedural texts paired with expert-annotated PDDL representations. Using this dataset, we evaluate state-of-the-art models on defining the preconditions and effects of actions. We show that Proc2PDDL is highly challenging, with GPT-3.5's success rate close to 0% and GPT-4's around 35%. Our analysis shows both syntactic and semantic errors, indicating LMs' deficiency in both generating domain-specific prgorams and reasoning about events. We hope this analysis and dataset helps future progress towards integrating the best of LMs and formal planning.