# BTGenBot: Behavior Tree Generation for Robotic Tasks with Lightweight LLMs

arXiv: https://arxiv.org/abs/2403.12761 · HTML: https://mlsanity.com/paper/2403.12761/

## Key facts

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

## Built on by (most cited first, 14 of 14)

- [Nadine: An LLM-driven Intelligent Social Robot with Affective Capabilities and Human-like Memory](https://mlsanity.com/paper/2405.20189/) (2024)
- [Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents](https://mlsanity.com/paper/2603.05517/) (2026)
- [SayComply: Grounding Field Robotic Tasks in Operational Compliance through Retrieval-Based Language Models](https://mlsanity.com/paper/2411.11323/) (2024)
- [The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare](https://mlsanity.com/paper/2411.03287/) (2024)
- [Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning](https://mlsanity.com/paper/2603.06084/) (2026)
- [MinionsLLM: a Task-adaptive Framework For The Training and Control of Multi-Agent Systems Through Natural Language](https://mlsanity.com/paper/2508.08283/) (2025)
- [LLM-Driven Self-Refinement for Embodied Drone Task Planning](https://mlsanity.com/paper/2508.15501/) (2025)
- [Interpretable Robot Control via Structured Behavior Trees and Large Language Models](https://mlsanity.com/paper/2508.09621/) (2025)
- [Robot guide with multi-agent control and automatic scenario generation with LLM](https://mlsanity.com/paper/2509.10317/) (2025)
- [VersualRL: Closed-Loop Verbal Reinforcement Learning with Visual Execution Feedback for Task-Level Robot Planning](https://mlsanity.com/paper/2603.22169/) (2026)
- [Contract-Grounded Behavior Tree Synthesis via Coding Agents](https://mlsanity.com/paper/2607.12220/) (2026)
- [Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework](https://mlsanity.com/paper/2609.13335/) (2026)
- [ORDER: A Fictitious-World Benchmark for Domain-Adaptive Embodied AI](https://mlsanity.com/paper/2609.22285/) (2026)
- [APTree: Extended Behavior Trees for Adaptive and Scalable Automated Robotic Task Planning in Construction](https://mlsanity.com/paper/2610.18523/) (2026)

## Abstract (arXiv)

This paper presents a novel approach to generating behavior trees for robots using lightweight large language models (LLMs) with a maximum of 7 billion parameters. The study demonstrates that it is possible to achieve satisfying results with compact LLMs when fine-tuned on a specific dataset. The key contributions of this research include the creation of a fine-tuning dataset based on existing behavior trees using GPT-3.5 and a comprehensive comparison of multiple LLMs (namely llama2, llama-chat, and code-llama) across nine distinct tasks. To be thorough, we evaluated the generated behavior trees using static syntactical analysis, a validation system, a simulated environment, and a real robot. Furthermore, this work opens the possibility of deploying such solutions directly on the robot, enhancing its practical applicability. Findings from this study demonstrate the potential of LLMs with a limited number of parameters in generating effective and efficient robot behaviors.