# LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning

arXiv: https://arxiv.org/abs/2409.10444 · HTML: https://mlsanity.com/paper/2409.10444/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2024.

## Built on by (most cited first, 19 of 19)

- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning](https://mlsanity.com/paper/2511.02424/) (2025)
- [AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules](https://mlsanity.com/paper/2604.07039/) (2026)
- [CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments](https://mlsanity.com/paper/2503.00729/) (2025)
- [Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation](https://mlsanity.com/paper/2503.08084/) (2025)
- [Robot Operation of Home Appliances by Reading User Manuals](https://mlsanity.com/paper/2505.20424/) (2025)
- [From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles](https://mlsanity.com/paper/2601.12358/) (2026)
- [Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning](https://mlsanity.com/paper/2603.06084/) (2026)
- [Sequential Planning via Anchored Robotic Keypoints](https://mlsanity.com/paper/2606.30613/) (2026)
- [LLM-Driven Self-Refinement for Embodied Drone Task Planning](https://mlsanity.com/paper/2508.15501/) (2025)
- [Sensory-Motor Control with Large Language Models via Iterative Policy Refinement](https://mlsanity.com/paper/2506.04867/) (2025)
- [A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation](https://mlsanity.com/paper/2603.08388/) (2026)
- [Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision](https://mlsanity.com/paper/2604.02812/) (2026)
- [Contract-Grounded Behavior Tree Synthesis via Coding Agents](https://mlsanity.com/paper/2607.12220/) (2026)
- [MaCoPlanner: LLM-Assisted Manual-Compiled Task Planning with Proactive Safety Verification for Robotic Industrial Panel Operation](https://mlsanity.com/paper/2608.28300/) (2026)
- [PanelShield: Verifiable Closed-Loop Safe Planning for Robotic Industrial Panel Operation](https://mlsanity.com/paper/2608.28305/) (2026)
- [CoAdapt: An LLM-based Framework for Adaptive Collaborative Perception in IIoT Robotic Swarms](https://mlsanity.com/paper/2609.16852/) (2026)
- [ORDER: A Fictitious-World Benchmark for Domain-Adaptive Embodied AI](https://mlsanity.com/paper/2609.22285/) (2026)

## Abstract (arXiv)

Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually can be effort-intensive. Large language models (LLMs) have recently been applied to robotic task planning for generating action sequences, yet their ability to generate BTs has not been fully investigated. To this end, we propose LLM-as-BT-Planner, a novel framework that leverages LLMs for BT generation in robotic assembly task planning. Four in-context learning methods are introduced to utilize the natural language processing and inference capabilities of LLMs for producing task plans in BT format, reducing manual effort while ensuring robustness and comprehensibility. Additionally, we evaluate the performance of fine-tuned smaller LLMs on the same tasks. Experiments in both simulated and real-world settings demonstrate that our framework enhances LLMs' ability to generate BTs, improving success rate through in-context learning and supervised fine-tuning.