mlsanityData to 7 Oct 2026

Behavior Trees Enable Structured Programming of Language Model Agents

arXiv 2404.07439 ↗First posted 11 Apr 2024cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Language models trained on internet-scale data sets have shown an impressive ability to solve problems in Natural Language Processing and Computer Vision. However, experience is showing that these models are frequently brittle in unexpected ways, and require significant scaffolding to ensure that they operate correctly in the larger systems that comprise "language-model agents." In this paper, we argue that behavior trees provide a unifying framework for combining language models with classical AI and traditional programming. We introduce Dendron, a Python library for programming language model agents using behavior trees. We demonstrate the approach embodied by Dendron in three case studies: building a chat agent, a camera-based infrastructure inspection agent for use on a mobile robot or vehicle, and an agent that has been built to satisfy safety constraints that it did not receive through instruction tuning or RLHF.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 31 of its 45 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

31 of 45 references.

References · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  9. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  10. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  11. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  12. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 250
19 more
  1. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  2. 2023EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anythingcited by 187
  3. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  4. 2023ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Promptscited by 160
  5. 2024Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Modelscited by 150
  6. 2017Behavior Trees in Robotics and AI: An Introductioncited by 105
  7. 2023Effective Prompt Extraction from Language Modelscited by 83
  8. 2023Mirages: On Anthropomorphism in Dialogue Systemscited by 30
  9. 2023LLM-BRAIn: AI-driven Fast Generation of Robot Behaviour Tree based on Large Language Modelcited by 23
  10. 2023Robot Behavior-Tree-Based Task Generation with Large Language Modelscited by 22
  11. 2020On modularity in reactive control architectures, with an application to formal verificationcited by 11
  12. 2015A Framework for Constrained and Adaptive Behavior-Based Agentscited by 8
  13. 2024Testing the Limits of Jailbreaking Defenses with the Purple Problemcited by 8
  14. 2018Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guaranteescited by 6
  15. 2023Designing Behavior Trees from Goal-Oriented LTLf Formulascited by 5
  16. 2024A Study on Training and Developing Large Language Models for Behavior Tree Generationcited by 4
  17. 2021Continuous-Time Behavior Trees as Discontinuous Dynamical Systemscited by 3
  18. 2022Verifying Safety of Behaviour Trees in Event-Bcited by 2
  19. 2023An Extended Convergence Result for Behaviour Tree Controllerscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
  2. 2026Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning
  3. 2024AutoGRAMS: Autonomous Graphical Agent Modeling Software
  4. 2024Tree Search for Language Model Agents
  5. 2023Towards A Unified Agent with Foundation Models
  6. 2025The Ann Arbor Architecture for Agent-Oriented Programming
  7. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
  8. 2026Exploration and Exploitation Errors Are Measurable for Language Model Agents