# Contract-Grounded Behavior Tree Synthesis via Coding Agents

arXiv: https://arxiv.org/abs/2607.12220 · HTML: https://mlsanity.com/paper/2607.12220/

## Key facts

- No citing papers in the map yet (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 21 of its 36 references that are in the map.
- First posted on arXiv 13 Jul 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, 21 of 21)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Behavior Trees in Robotics and AI: An Introduction](https://mlsanity.com/paper/1709.00084/) (2017)
- [The Marathon 2: A Navigation System](https://mlsanity.com/paper/2003.00368/) (2020)
- [A Survey of Behavior Trees in Robotics and AI](https://mlsanity.com/paper/2005.05842/) (2020)
- [Deploying and Evaluating LLMs to Program Service Mobile Robots](https://mlsanity.com/paper/2311.11183/) (2023)
- [RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks](https://mlsanity.com/paper/2603.11558/) (2026)
- [LLM-BRAIn: AI-driven Fast Generation of Robot Behaviour Tree based on Large Language Model](https://mlsanity.com/paper/2305.19352/) (2023)
- [Robot Behavior-Tree-Based Task Generation with Large Language Models](https://mlsanity.com/paper/2302.12927/) (2023)
- [Towards Blended Reactive Planning and Acting using Behavior Trees](https://mlsanity.com/paper/1611.00230/) (2016)
- [LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning](https://mlsanity.com/paper/2409.10444/) (2024)
- [LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems](https://mlsanity.com/paper/2312.09348/) (2023)
- [Representing Robot Task Plans as Robust Logical-Dynamical Systems](https://mlsanity.com/paper/1908.01896/) (2019)
- [Learning of Behavior Trees for Autonomous Agents](https://mlsanity.com/paper/1504.05811/) (2015)
- [BTGenBot: Behavior Tree Generation for Robotic Tasks with Lightweight LLMs](https://mlsanity.com/paper/2403.12761/) (2024)
- [Behavior Trees in Robot Control Systems](https://mlsanity.com/paper/2203.13083/) (2022)
- [Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions](https://mlsanity.com/paper/2405.07474/) (2024)
- [Automatic Behavior Tree Expansion with LLMs for Robotic Manipulation](https://mlsanity.com/paper/2409.13356/) (2024)
- [A Study on Training and Developing Large Language Models for Behavior Tree Generation](https://mlsanity.com/paper/2401.08089/) (2024)

## Abstract (arXiv)

Synthesizing deployable robot behavior trees (BTs) from natural language (NL) requires grounding to ensure every generated BT references only skills a robot can actually execute. Existing LLM-based BT synthesis approaches often place this grounding responsibility on the prompt author. This makes deployment brittle when the author does not know which skills the robot can execute, how those skills are parameterized, or how the robot runtime software constrains valid BT structure. This paper proposes a contract-grounded BT synthesis architecture in which a coding agent queries a robot-side Model Context Protocol (MCP) server to retrieve an explicit contract consisting of a skill library, permitted BT operators, and optional BT composition templates, before synthesizing a BT for validation and execution. In our framework, non-expert operators issue NL commands without knowledge of robot implementation details, while a robot runtime validation gate enforces correctness before execution. We evaluate two LLMs, a closed model (Sonnet 4.6) and a smaller open-source model (Gemma4:31b), across 110 simulated tasks in PyRoboSim and 14 tasks on a physical Husarion Panther robot. Results show that contract grounding enables near-perfect BT validation and high task success, that BT composition templates substantially recover success on reactive control-flow tasks for the smaller model, and that the architecture transfers to physical hardware running a Nav2 stack opaque to both operator and agent.