通过分层协作与记忆整合，提升多智能体系统任务分配效率。
MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation
- 构建管理者-成员层级结构，全局分配任务避免冲突。
- 引入情景记忆整合模块，保留长期上下文信息。
- 在复杂协作任务中表现优于现有方法，适应性强。
大型语言模型（LLMs）的进展显著推动了具身智能体的发展。基于LLM的多智能体系统缓解了单智能体在复杂任务中的低效问题，但仍存在记忆不一致和行为冲突等挑战。为此，我们提出MiTa，一种分层的记忆集成任务分配框架，以提升协作效率。MiTa将智能体组织为管理者-成员层级结构，管理者集成任务分配与摘要模块，实现（1）全局任务分配，（2）情景记忆整合。分配模块使管理者从全局视角进行任务分配，避免潜在的智能体间冲突；摘要模块在任务进度更新时触发，通过将近期协作历史压缩为简洁摘要，实现情景记忆整合，保留长时上下文。结合任务分配与情景记忆，MiTa获得更清晰的任务理解，促进全局一致的任务分配。实验结果表明，相较于强基线方法，MiTa在复杂多智能体协作中表现出更优的效率与适应性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。