# Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation

arXiv: https://arxiv.org/abs/2603.06064 · HTML: https://mlsanity.com/paper/2603.06064/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 34 of its 36 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 34)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks](https://mlsanity.com/paper/2402.08115/) (2024)
- [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [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)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning](https://mlsanity.com/paper/2308.13724/) (2023)
- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2404.03275/) (2024)
- [Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds](https://mlsanity.com/paper/2305.17590/) (2023)
- [Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code](https://mlsanity.com/paper/2503.18809/) (2025)
- [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://mlsanity.com/paper/2407.12979/) (2024)
- [Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts](https://mlsanity.com/paper/2409.15915/) (2024)
- [LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Model](https://mlsanity.com/paper/2311.17406/) (2023)
- [Generating consistent PDDL domains with Large Language Models](https://mlsanity.com/paper/2404.07751/) (2024)
- [Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition](https://mlsanity.com/paper/2409.19250/) (2024)
- [LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions](https://mlsanity.com/paper/2501.00830/) (2025)
- [LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning](https://mlsanity.com/paper/2409.01806/) (2024)

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

- [Neurosymbolic Embodied Agents](https://mlsanity.com/paper/2608.16794/) (2026)

## Abstract (arXiv)

Task planning, the problem of sequencing actions to reach a goal from an initial state, is a core capability requirement for autonomous robotic systems. Whether large language models (LLMs) can serve as viable planners alongside classical symbolic methods remains an open question. We present PyPDDLEngine, an open-source Planning Domain Definition Language (PDDL) simulation engine that exposes planning operations as LLM tool calls through a Model Context Protocol (MCP) interface. Rather than committing to a complete action sequence upfront, the LLM acts as an interactive search policy that selects one action at a time, observes each resulting state, and can reset and retry. We evaluate four approaches on 102 International Planning Competition (IPC) Blocksworld instances under a uniform 180-second budget: Fast Downward lama-first and seq-sat-lama-2011 as classical baselines, direct LLM planning (Claude Haiku 4.5), and agentic LLM planning via PyPDDLEngine. Fast Downward achieves 85.3% success. The direct and agentic LLM approaches achieve 63.7% and 66.7%, respectively, a consistent but modest three-percentage-point advantage for the agentic approach at 5.7× higher token cost per solution. Across most co-solved difficulty blocks, both LLM approaches produce shorter plans than seq-sat-lama-2011 despite its iterative quality improvement, a result consistent with training-data recall rather than generalisable planning. These results suggest that agentic gains depend on the nature of environmental feedback. Coding agents benefit from externally grounded signals such as compiler errors and test failures, whereas PDDL step feedback is self-assessed, leaving the agent to evaluate its own progress without external verification.