# EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration

arXiv: https://arxiv.org/abs/2601.11063 · HTML: https://mlsanity.com/paper/2601.11063/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [Translating Natural Language to Planning Goals with Large-Language Models](https://mlsanity.com/paper/2302.05128/) (2023)
- [Dynamic Planning with a LLM](https://mlsanity.com/paper/2308.06391/) (2023)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models](https://mlsanity.com/paper/2403.17246/) (2024)
- [Large Language Models for Multi-Robot Systems: A Survey](https://mlsanity.com/paper/2502.03814/) (2025)
- [Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning](https://mlsanity.com/paper/2504.17950/) (2025)
- [Probabilistically Correct Language-based Multi-Robot Planning using Conformal Prediction](https://mlsanity.com/paper/2402.15368/) (2024)
- [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://mlsanity.com/paper/2407.12979/) (2024)
- [An Overview of Hierarchical Task Network Planning](https://mlsanity.com/paper/1403.7426/) (2014)
- [BodyGen: Advancing Towards Efficient Embodiment Co-Design](https://mlsanity.com/paper/2503.00533/) (2025)
- [LLM-HBT: Dynamic Behavior Tree Construction for Adaptive Coordination in Heterogeneous Robots](https://mlsanity.com/paper/2510.09963/) (2025)
- [Curriculum Imitation Learning of Distributed Multi-Robot Policies](https://mlsanity.com/paper/2509.25097/) (2025)

## Built on by (most cited first, 2 of 2)

- [Verification-Gated Agentic Mission-State Governance for Intelligent Industrial Multi-Robot Systems](https://mlsanity.com/paper/2606.31339/) (2026)
- [Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs](https://mlsanity.com/paper/2608.22657/) (2026)

## Abstract (arXiv)

In embodied artificial intelligence, enabling heterogeneous robot teams to execute long-horizon tasks from high-level instructions remains a critical challenge. While large language models (LLMs) show promise in instruction parsing and preliminary planning, they exhibit limitations in long-term reasoning and dynamic multi-robot coordination. We propose EmboTeam, a novel embodied multi-robot task planning framework that addresses these issues through a three-stage cascaded architecture: 1) It leverages an LLM to parse instructions and generate Planning Domain Definition Language (PDDL) problem descriptions, thereby transforming commands into formal planning problems; 2) It combines the semantic reasoning of LLMs with the search capabilities of a classical planner to produce optimized action sequences; 3) It compiles the resulting plan into behavior trees for reactive control. The framework supports dynamically sized heterogeneous robot teams via a shared blackboard mechanism for communication and state synchronization. To validate our approach, we introduce the MACE-THOR benchmark dataset, comprising 42 complex tasks across 8 distinct household layouts. Experiments show EmboTeam improves the task success rate from 12% to 55% and goal condition recall from 32% to 72% over the LaMMA-P baseline.