MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation
This addresses inefficiencies in multi-agent collaboration for embodied AI, though it appears incremental as it builds on existing hierarchical and memory-based approaches.
The paper tackles memory inconsistency and behavioral conflicts in LLM-based multi-agent systems by proposing MiTa, a hierarchical framework with memory integration and task allocation, which achieves superior efficiency and adaptability in complex tasks compared to baseline methods.
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.