# MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model

arXiv: https://arxiv.org/abs/2403.18760 · HTML: https://mlsanity.com/paper/2403.18760/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2024.

## Built on by (most cited first, 15 of 15)

- [SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents](https://mlsanity.com/paper/2412.13178/) (2024)
- [IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks](https://mlsanity.com/paper/2506.16402/) (2025)
- [Autonomous Improvement of Instruction Following Skills via Foundation Models](https://mlsanity.com/paper/2407.20635/) (2024)
- [SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents](https://mlsanity.com/paper/2509.25885/) (2025)
- [ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent](https://mlsanity.com/paper/2507.18165/) (2025)
- [Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification](https://mlsanity.com/paper/2504.04578/) (2025)
- [REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation](https://mlsanity.com/paper/2503.22122/) (2025)
- [Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models](https://mlsanity.com/paper/2501.02026/) (2025)
- [Long-horizon Embodied Planning with Implicit Logical Inference and Hallucination Mitigation](https://mlsanity.com/paper/2409.15658/) (2024)
- [LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning](https://mlsanity.com/paper/2503.08508/) (2025)
- [Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis](https://mlsanity.com/paper/2602.08276/) (2026)
- [NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning](https://mlsanity.com/paper/2605.09387/) (2026)
- [TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning](https://mlsanity.com/paper/2605.18109/) (2026)
- [Enhancing Part-Level Point Grounding for Any Open-Source MLLMs](https://mlsanity.com/paper/2606.29267/) (2026)
- [Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation](https://mlsanity.com/paper/2608.22800/) (2026)

## Abstract (arXiv)

In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innovatively decomposes tasks at the goal-level, task-level, and action-level to mitigate the challenge of complex long-horizon tasks. In order to enhance open-source LLMs' planning abilities, we introduce a goal-sensitive corpus generation method to create high-quality training data and conduct instruction tuning on the generated corpus. Since the complexity of the existing datasets is not high enough, we construct a more challenging dataset, LongTasks, to specifically evaluate planning ability on complex long-horizon tasks. We evaluate our method using various LLMs on four datasets in VirtualHome. Our results demonstrate a significant performance enhancement in robotic task planning, showcasing MLDT's effectiveness in overcoming the limitations of existing methods based on open-source LLMs as well as its practicality in complex, real-world scenarios.