# Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning

arXiv: https://arxiv.org/abs/2602.21670 · HTML: https://mlsanity.com/paper/2602.21670/

## Key facts

- Cited by 2 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 17 of its 23 references that are in the map.
- First posted on arXiv 25 Feb 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, 17 of 17)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [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)
- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2309.10062/) (2023)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?](https://mlsanity.com/paper/2309.15943/) (2023)
- [DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2404.03275/) (2024)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner](https://mlsanity.com/paper/2409.20560/) (2024)
- [LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planning](https://mlsanity.com/paper/2410.21040/) (2024)
- [Probabilistically Correct Language-based Multi-Robot Planning using Conformal Prediction](https://mlsanity.com/paper/2402.15368/) (2024)
- [CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning](https://mlsanity.com/paper/2410.22225/) (2024)
- [Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development](https://mlsanity.com/paper/2505.16086/) (2025)

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

- [Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution](https://mlsanity.com/paper/2606.20014/) (2026)
- [Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method](https://mlsanity.com/paper/2609.35965/) (2026)

## Abstract (arXiv)

Multi-robot task planning requires decomposing natural-language instructions into executable actions for heterogeneous robot teams. Conventional Planning Domain Definition Language (PDDL) planners provide rigorous guarantees but struggle to handle ambiguous or long-horizon missions, while large language models (LLMs) can interpret instructions and propose plans but may hallucinate or produce infeasible actions. We present a hierarchical multi-agent LLM-based planner with prompt optimization: an upper layer decomposes tasks and assigns them to lower-layer agents, which generate PDDL problems solved by a classical planner. When plans fail, the system applies TextGrad-inspired textual-gradient updates to optimize each agent's prompt and thereby improve planning accuracy. In addition, meta-prompts are learned and shared across agents within the same layer, enabling efficient prompt optimization in multi-agent settings. On the MAT-THOR benchmark, our planner achieves success rates of 0.95 on compound tasks, 0.84 on complex tasks, and 0.60 on vague tasks, improving over the previous state-of-the-art LaMMA-P by 2, 7, and 15 percentage points respectively. An ablation study shows that the hierarchical structure, prompt optimization, and meta-prompt sharing contribute roughly +59, +37, and +4 percentage points to the overall success rate.