# One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

arXiv: https://arxiv.org/abs/2505.18382 · HTML: https://mlsanity.com/paper/2505.18382/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2025.

## Built on by (most cited first, 5 of 5)

- [StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation](https://mlsanity.com/paper/2609.20791/) (2026)
- [PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty](https://mlsanity.com/paper/2606.15654/) (2026)
- [GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning](https://mlsanity.com/paper/2608.07905/) (2026)
- [Neurosymbolic Embodied Agents](https://mlsanity.com/paper/2608.16794/) (2026)
- [VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation](https://mlsanity.com/paper/2609.33464/) (2026)

## Abstract (arXiv)

Pre-trained large language models (LLMs) show promise for robotic task planning but often struggle to guarantee correctness in long-horizon problems. Task and motion planning (TAMP) addresses this by grounding symbolic plans in low-level execution, yet it relies heavily on manually engineered planning domains. To improve long-horizon planning reliability and reduce human intervention, we present Planning Domain Derivation with LLMs (PDDLLM), a framework that automatically induces symbolic predicates and actions directly from demonstration trajectories by combining LLM reasoning with physical simulation roll-outs. Unlike prior domain-inference methods that rely on partially predefined or language descriptions of planning domains, PDDLLM constructs domains without manual domain initialization and automatically integrates them with motion planners to produce executable plans, enhancing long-horizon planning automation. Across 1,200 tasks in nine environments, PDDLLM outperforms six LLM-based planning baselines, achieving at least 20% higher success rates, reduced token costs, and successful deployment on multiple physical robot platforms.