# LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems arXiv: https://arxiv.org/abs/2312.09348 ยท HTML: https://mlsanity.com/paper/2312.09348/ ## Key facts - Cited by 18 papers in the map (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 27 of its 52 references that are in the map. - First posted on arXiv 14 Dec 2023. ## 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, 27 of 27) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023) - [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023) - [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023) - [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022) - [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023) - [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020) - [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022) - [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023) - [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022) - [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022) - [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023) - [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022) - [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022) - [Task and Motion Planning with Large Language Models for Object Rearrangement](https://mlsanity.com/paper/2303.06247/) (2023) - [Behavior Trees in Robotics and AI: An Introduction](https://mlsanity.com/paper/1709.00084/) (2017) - [Embodied Task Planning with Large Language Models](https://mlsanity.com/paper/2307.01848/) (2023) - [How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks](https://mlsanity.com/paper/2303.00293/) (2023) - [Chat with the Environment: Interactive Multimodal Perception Using Large Language Models](https://mlsanity.com/paper/2303.08268/) (2023) - [Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs](https://mlsanity.com/paper/2304.14999/) (2023) - [Robot Behavior-Tree-Based Task Generation with Large Language Models](https://mlsanity.com/paper/2302.12927/) (2023) - [Behavior Trees in Robot Control Systems](https://mlsanity.com/paper/2203.13083/) (2022) - [Behavior Trees and State Machines in Robotics Applications](https://mlsanity.com/paper/2208.04211/) (2022) - [On the Implementation of Behavior Trees in Robotics](https://mlsanity.com/paper/2106.15227/) (2021) - [Task Planning with Belief Behavior Trees](https://mlsanity.com/paper/2008.09393/) (2020) ## Built on by (most cited first, 18 of 18) - [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) - [Large Language Models for Multi-Robot Systems: A Survey](https://mlsanity.com/paper/2502.03814/) (2025) - [RaceVLA: VLA-based Racing Drone Navigation with Human-like Behaviour](https://mlsanity.com/paper/2503.02572/) (2025) - [Bi-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Dexterous Manipulations](https://mlsanity.com/paper/2405.06039/) (2024) - [Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions](https://mlsanity.com/paper/2405.07474/) (2024) - [Nadine: An LLM-driven Intelligent Social Robot with Affective Capabilities and Human-like Memory](https://mlsanity.com/paper/2405.20189/) (2024) - [From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems](https://mlsanity.com/paper/2506.04565/) (2025) - [Industry 6.0: New Generation of Industry driven by Generative AI and Swarm of Heterogeneous Robots](https://mlsanity.com/paper/2409.10106/) (2024) - [HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning](https://mlsanity.com/paper/2406.00965/) (2024) - [MRBTP: Efficient Multi-Robot Behavior Tree Planning and Collaboration](https://mlsanity.com/paper/2502.18072/) (2025) - [PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language](https://mlsanity.com/paper/2510.22784/) (2025) - [From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles](https://mlsanity.com/paper/2601.12358/) (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) - [Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges](https://mlsanity.com/paper/2605.02592/) (2026) - [Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation](https://mlsanity.com/paper/2408.08188/) (2024) - [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) ## Abstract (arXiv) This paper introduces LLM-MARS, first technology that utilizes a Large Language Model based Artificial Intelligence for Multi-Agent Robot Systems. LLM-MARS enables dynamic dialogues between humans and robots, allowing the latter to generate behavior based on operator commands and provide informative answers to questions about their actions. LLM-MARS is built on a transformer-based Large Language Model, fine-tuned from the Falcon 7B model. We employ a multimodal approach using LoRa adapters for different tasks. The first LoRa adapter was developed by fine-tuning the base model on examples of Behavior Trees and their corresponding commands. The second LoRa adapter was developed by fine-tuning on question-answering examples. Practical trials on a multi-agent system of two robots within the Eurobot 2023 game rules demonstrate promising results. The robots achieve an average task execution accuracy of 79.28% in compound commands. With commands containing up to two tasks accuracy exceeded 90%. Evaluation confirms the system's answers on operators questions exhibit high accuracy, relevance, and informativeness. LLM-MARS and similar multi-agent robotic systems hold significant potential to revolutionize logistics, enabling autonomous exploration missions and advancing Industry 5.0.