Contract-Grounded Behavior Tree Synthesis via Coding Agents

• URL: http://arxiv.org/abs/2607.12220v1
• Date: Mon, 13 Jul 2026 23:41:16 GMT
• Title: Contract-Grounded Behavior Tree Synthesis via Coding Agents
• Abstract summary: Existing LLM-based BT synthesis approaches often place this grounding responsibility on the prompt author.<n>This paper proposes a contract-grounded BT synthesis architecture in which a coding agent queries a robot-side Model Context Protocol (MCP) server.<n>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.
• Score: 2.593510481959727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Few Words Go a Long Way: Language Guided Robot Policy Synthesis [9.088404024682706]
  ARCHITECT is a framework that treats robot policy acquisition as an interactive program synthesis task.<n>We introduce an iterative process where a human supervisor provides natural language corrections to steer the policy.<n>In a benchmark evaluation on a Franka Panda robot, ARCHITECT outperforms state-of-the-art VLA models.
  arXiv  Detail & Related papers  (2026-07-26T18:00:02Z)
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation [36.70100723410325]
  Behavior Trees (BTs) offer a powerful paradigm for designing modular and reactive robot controllers.<n>BT planning provides theoretical guarantees for the automated generation of reliable BTs.<n>We introduce CABTO, the first framework to efficiently solve the BT Grounding problem.
  arXiv  Detail & Related papers  (2026-03-17T17:12:46Z)
• BTGenBot-2: Efficient Behavior Tree Generation with Small Language Models [7.802379200026965]
  BTGenBot-2 is an open-source small language model that converts natural language task descriptions and a list of robot action primitives into executable behavior trees in XML.<n>Unlike prior approaches, BTGenBot-2 enables zero-shot BT generation, error recovery at inference and runtime, while remaining lightweight enough for resource-constrained robots.<n>Extensive evaluations demonstrate that BTGenBot-2 consistently outperforms GPT-5, Claude Opus 4.1, and larger open-source models across both functional and non-functional metrics.
  arXiv  Detail & Related papers  (2026-02-02T09:43:17Z)
• Behavior Trees vs Executable Ontologies: a Comparative Analysis of Robot Control Paradigms [51.56484100374058]
  We compare two approaches to modeling robotic behavior: imperative Behavior Trees (BTs) and declarative Executable Ontologies (EO)<n>BTs structure behavior hierarchically using control-flow, whereas EO represents the domain as a temporal, event-based semantic graph driven by dataflow rules.
  arXiv  Detail & Related papers  (2025-11-19T09:38:01Z)
• Heterogeneous Robot Collaboration in Unstructured Environments with Grounded Generative Intelligence [54.91177026001217]
  Large language model (LLM)-enabled teaming methods typically assume well-structured and known environments.<n>We present SPINE-HT, a framework that addresses these limitations by grounding the reasoning abilities of LLMs in the context of a heterogeneous robot team.<n>Our framework achieves nearly twice the success rate compared to prior LLM-enabled heterogeneous teaming approaches.
  arXiv  Detail & Related papers  (2025-10-30T18:24:38Z)
• Robotic Control via Embodied Chain-of-Thought Reasoning [86.6680905262442]
  Key limitation of learned robot control policies is their inability to generalize outside their training data.<n>Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language models can substantially improve their robustness and generalization ability.<n>We introduce Embodied Chain-of-Thought Reasoning (ECoT) for VLAs, in which we train VLAs to perform multiple steps of reasoning about plans, sub-tasks, motions, and visually grounded features before predicting the robot action.
  arXiv  Detail & Related papers  (2024-07-11T17:31:01Z)
• Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions [5.31484618181979]
  Behavior Tree (BT) is an appropriate control architecture for robots executing tasks following human instructions. This paper proposes a two-stage framework for BT generation, which first employs large language models to interpret goals from high-level instructions. We represent goals as well-formed formulas in first-order logic, effectively bridging intent understanding and optimal behavior planning.
  arXiv  Detail & Related papers  (2024-05-13T05:23:48Z)
• RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation [77.41969287400977]
  This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation. We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
  arXiv  Detail & Related papers  (2024-02-22T15:12:00Z)
• ProgPrompt: Generating Situated Robot Task Plans using Large Language Models [68.57918965060787]
  Large language models (LLMs) can be used to score potential next actions during task planning. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments.
  arXiv  Detail & Related papers  (2022-09-22T20:29:49Z)
• Behavior Tree-Based Asynchronous Task Planning for Multiple Mobile Robots using a Data Distribution Service [2.6667914906637487]
  We propose a task planning framework for multiple robots that builds on a behavior tree (BT) To plan tasks for robots efficiently, a single task planning unit is implemented with the proposed task types. Three mobile robots were experimentally coordinated for them to travel alternately to four goal positions by the proposed single task planning unit.
  arXiv  Detail & Related papers  (2022-01-26T13:16:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.