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

2026-01-30

AI Summary

This work addresses the challenge of inefficient collaboration in multi-agent systems caused by inconsistent memory and behavioral conflicts during complex tasks. To mitigate these issues, the authors propose a hierarchical collaboration framework featuring a manager-member architecture. The framework employs a task allocation module to coordinate agent behaviors and prevent conflicts, alongside a contextual memory summarization mechanism that compresses collaborative history while preserving long-range contextual information. This approach effectively integrates global task planning with local execution, substantially enhancing both consistency and efficiency in multi-agent collaboration. Experimental results demonstrate that the proposed framework significantly outperforms strong baseline methods across a variety of complex multi-agent tasks, exhibiting superior adaptability and scalability.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Multi-Robot Systems

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• memory inconsistency
• agent behavioral conflicts
• multi-agent collaboration
• task allocation
• episodic memory

Innovation

• hierarchical multi-agent collaboration
• memory integration
• task allocation
• episodic memory
• LLM-based agents