StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management
Authors: Ruizhe Zhang, Xinke Jiang, Zhibang Yang, Zhixin Zhang, Jiaran Gao, Yuzhen Xiao, Tao Feng, Yue Fang, +7 more
Organizations: School of Computer Science, Peking University, Beijing, China · 2National Engineering Research Center for Software Engineering, Peking University, Beijing, China · 3Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China · School of Public Affaris, Zhejiang University, Hangzhou, China · School of Software & Microelectronics, Peking University, Beijing, China · 6GRG Banking Equipment Co., Ltd., Guangzhou, China · Center on Frontiers of Computing Studies, Peking University, Beijing, China · 8Peking University Information Technology Institute (Tianjin Binhai), Tianjin, China
Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon collaboration due to the lack of memory management, leading to context bloat, error accumulation, and poor cross-task generalization. To address both task-level memory inefficiency and the inability to reuse coordination experience, we propose StackPlanner, a hierarchical multi-agent framework with explicit memory control. StackPlanner addresses these challenges by decoupling high-level coordination from subtask execution with active task-level memory control, and by learning to retrieve and exploit reusable coordination experience via structured experience memory and reinforcement learning. Experiments on multiple deep-search and agent system benchmarks demonstrate the effectiveness of our approach in enabling reliable long-horizon multi-agent collaboration.