# PDDL-ART: Autonomous Symbolic Abstraction From Demonstration For Long-Horizon Robotic Manipulation Using Vision-Language Models

arXiv: https://arxiv.org/abs/2608.17146 · HTML: https://mlsanity.com/paper/2608.17146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [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)
- [Autoformalization with Large Language Models](https://mlsanity.com/paper/2205.12615/) (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)
- [Predicate Invention for Bilevel Planning](https://mlsanity.com/paper/2203.09634/) (2022)
- [Guiding Long-Horizon Task and Motion Planning with Vision Language Models](https://mlsanity.com/paper/2410.02193/) (2024)
- [STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning](https://mlsanity.com/paper/2412.15182/) (2024)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [Grounding Predicates through Actions](https://mlsanity.com/paper/2109.14718/) (2021)
- [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)
- [Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning](https://mlsanity.com/paper/2509.13351/) (2025)
- [From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models](https://mlsanity.com/paper/2501.00296/) (2024)
- [From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning](https://mlsanity.com/paper/2402.11871/) (2024)
- [UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning](https://mlsanity.com/paper/2507.21545/) (2025)
- [Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning](https://mlsanity.com/paper/2510.03182/) (2025)
- [LLM-GROP: Visually Grounded Robot Task and Motion Planning with Large Language Models](https://mlsanity.com/paper/2511.07727/) (2025)
- [Vision Language Models Cannot Plan, but Can They Formalize?](https://mlsanity.com/paper/2509.21576/) (2025)
- [Using VLM Reasoning to Constrain Task and Motion Planning](https://mlsanity.com/paper/2510.25548/) (2025)
- [Language-Guided Object Search in Agricultural Environments](https://mlsanity.com/paper/2503.01068/) (2025)

## Abstract (arXiv)

Symbolic planning with PDDL offers a principled framework for long-horizon robot manipulation, but constructing accurate PDDL domain and problem descriptions remains a significant bottleneck, typically requiring substantial domain expertise. We present a Vision-Language Model (VLM)-based approach called PDDL-ART, a framework that autonomously generates task-specific PDDL domain and problem descriptions from a single expert demonstration, a natural language task description, and a library of available high-level action names. PDDL-ART does not require any domain templates, action signatures, or fine-tuning. To ensure the generated descriptions are not only syntactically valid but semantically aligned with the demonstrated task, PDDL-ART introduces a multi-stage correction pipeline operating at syntactic, semantic, and execution levels. A key component of execution-guided correction is symbolic predicate grounding. Instead of relying solely on visual observations, PDDL-ART leverages the tool-use capabilities of modern VLMs to incorporate geometric and temporal reasoning for evaluating relational predicates that are not directly discernible from images alone. Critically, the model autonomously determines when to invoke these tools and how to interpret their outputs. We evaluate PDDL-ART on challenging manipulation tasks in engine maintenance and household domains, including tasks that require memory, abstract predicate inference, and goal states that are visually indistinguishable from the initial state. PDDL-ART achieves an average success rate of 93.3%, compared to 78.3% for a baseline VLM-based planner.