MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation

TL;DR

MiTa is a hierarchical multi-agent framework that integrates memory and task allocation to improve collaboration efficiency and consistency in complex tasks involving large language models.

Contribution

It introduces a hierarchical structure with memory integration and global task allocation, addressing memory inconsistency and behavioral conflicts in multi-agent systems.

Findings

Achieves higher efficiency in multi-agent cooperation.

Demonstrates improved adaptability in complex tasks.

Outperforms baseline methods in experiments.

Abstract

Recent advances in large language models (LLMs) have substantially accelerated the development of embodied agents. LLM-based multi-agent systems mitigate the inefficiency of single agents in complex tasks. However, they still suffer from issues such as memory inconsistency and agent behavioral conflicts. To address these challenges, we propose MiTa, a hierarchical memory-integrated task allocative framework to enhance collaborative efficiency. MiTa organizes agents into a manager-member hierarchy, where the manager incorporates additional allocation and summary modules that enable (1) global task allocation and (2) episodic memory integration. The allocation module enables the manager to allocate tasks from a global perspective, thereby avoiding potential inter-agent conflicts. The summary module, triggered by task progress updates, performs episodic memory integration by condensing recent collaboration history into a concise summary that preserves long-horizon context. By combining task allocation with episodic memory, MiTa attains a clearer understanding of the task and facilitates globally consistent task distribution. Experimental results confirm that MiTa achieves superior efficiency and adaptability in complex multi-agent cooperation over strong baseline methods.