# A Taxonomy of Hierarchical Multi-Agent Systems: Design Patterns, Coordination Mechanisms, and Industrial Applications

arXiv: https://arxiv.org/abs/2508.12683 · HTML: https://mlsanity.com/paper/2508.12683/

## Key facts

- Cited by 8 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 6 of its 26 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## 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, 6 of 6)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ROMA: Multi-Agent Reinforcement Learning with Emergent Roles](https://mlsanity.com/paper/2003.08039/) (2020)
- [Multi-Agent Coordination across Diverse Applications: A Survey](https://mlsanity.com/paper/2502.14743/) (2025)
- [Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning](https://mlsanity.com/paper/1901.08492/) (2019)
- [Vehicle Routing Problems for Drone Delivery](https://mlsanity.com/paper/1608.02305/) (2016)
- [Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks](https://mlsanity.com/paper/2407.08164/) (2024)

## Built on by (most cited first, 8 of 8)

- [InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents](https://mlsanity.com/paper/2601.03204/) (2026)
- [InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios](https://mlsanity.com/paper/2509.22502/) (2025)
- [A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process Control](https://mlsanity.com/paper/2606.30877/) (2026)
- [Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions](https://mlsanity.com/paper/2601.08156/) (2026)
- [Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance](https://mlsanity.com/paper/2602.16738/) (2026)
- [LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms](https://mlsanity.com/paper/2601.03328/) (2026)
- [Harnessing Implicit Cooperation: A Multi-Agent Reinforcement Learning Approach Towards Decentralized Local Energy Markets](https://mlsanity.com/paper/2602.16062/) (2026)
- [When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling](https://mlsanity.com/paper/2605.13172/) (2026)

## Abstract (arXiv)

Hierarchical multi-agent systems (HMAS) organize collections of agents into layered structures that help manage complexity and scale. These hierarchies can simplify coordination, but they also can introduce trade-offs that are not always obvious. This paper proposes a multi-dimensional taxonomy for HMAS along five axes: control hierarchy, information flow, role and task delegation, temporal layering, and communication structure. The intent is not to prescribe a single "best" design but to provide a lens for comparing different approaches. Rather than treating these dimensions in isolation, the taxonomy is connected to concrete coordination mechanisms - from the long-standing contract-net protocol for task allocation to more recent work in hierarchical reinforcement learning. Industrial contexts illustrate the framework, including power grids and oilfield operations, where agents at production, maintenance, and supply levels coordinate to diagnose well issues or balance energy demand. These cases suggest that hierarchical structures may achieve global efficiency while preserving local autonomy, though the balance is delicate. The paper closes by identifying open challenges: making hierarchical decisions explainable to human operators, scaling to very large agent populations, and assessing whether learning-based agents such as large language models can be safely integrated into layered frameworks. This paper presents what appears to be the first taxonomy that unifies structural, temporal, and communication dimensions of hierarchical MAS into a single design framework, bridging classical coordination mechanisms with modern reinforcement learning and large language model agents.