Cooperative Scheduling and Hierarchical Memory Model for Multi-Agent Systems
Abstract
Large Language Models (LLMs) are leading a technological revolution. This gives agents based on LLMs renewed vitality, and multi-agent collaboration is showing the potential to foster new forms of intelligence. However, current multi-agent systems face two major challenges: the first is the issue of resource coordination and scheduling within multi-agent systems, and the second is the limitation of the context window in large models, which hinders the practical application of agents in long-term conversational scenarios, urgently requiring improvements in memory capabilities. To address these challenges, we propose a collaborative scheduling strategy and hierarchical memory model for LLM-based multi-agent systems inspired by operating systems. First, we design a time-sharing scheduling strategy, analogous to process scheduling in operating systems, which divides the resource usage cycle into finer-grained single-step workflows, allocating independent resource windows to different agents to reduce resource contention and conflicts. Second, we introduce a hierarchical memory model based on the multi-level cache architecture of operating systems, segmenting the agents' memory into core memory, main memory, and vague memory areas, thereby significantly improving memory retention and retrieval efficiency in LLM - based agents when handling complex tasks. Experimental results demonstrate that our proposed method achieves efficient resource allocation in multi-agent systems while si…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Recent work has emphasised the importance of memory control mechanisms during inference, which determine what, when, and how to store, update, or discard memory.
“Recent work has also emphasised the importance of memory control mechanisms during inference (Zou et al., 2024; Chen et al., 2025d), which determine what, when, and how to store, update, or discard memory (Jin et al., 2025).”
From A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems (2025) · cites this paper as Zou et al., 2024
Cites
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · cited 1× · see citing works
“By calculating the cosine similarity [26] between memory entries and the user input, the system evaluates the relevance of memory entries to the current task and returns the most suitable memory information.”
Large Language Model Based Multi-agents: A Survey of Progress and Challenges
Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024) · Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2024/890 · Cited by 851 · see citing works
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., & Li, Q. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671470 · Cited by 827 · see citing works
Denning, P. J. (2005) · Communications of the ACM · doi:10.1145/1070838.1070856 · Cited by 280 · see citing works
WebGPT: Browser-assisted question-answering with human feedback
Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.09332 · Cited by 272 · see citing works
MemoryBank: Enhancing Large Language Models with Long-Term Memory
Zhong, W., Guo, L., Gao, Q., Ye, H., & Wang, Y. (2023) · arXiv · doi:10.48550/arxiv.2305.10250 · Cited by 253 · see citing works
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 214 · cited 1× · see citing works
“In contrast, multi-agent systems consist of multiple agents working collaboratively, with each agent responsible for specific tasks or interacting within different contexts [10]–[12].”
A Survey on the Memory Mechanism of Large Language Model-based Agents
Zhang, Z., Dai, Q., Bo, X., Ma, C., Li, R., Chen, X., Zhu, J., Dong, Z., & Wen, J.-R. (2025) · ACM Transactions on Information Systems · doi:10.1145/3748302 · Cited by 118 · see citing works
Self-citationHuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge
Wang, H., Liu, C., Xi, N., Qiang, Z., Zhao, S., Qin, B., & Liu, T. (2023) · arXiv · doi:10.48550/arxiv.2304.06975 · Cited by 115 · see citing works
Improving Factuality and Reasoning in Language Models through Multiagent Debate
Du, Y., Li, S., Torralba, A., Tenenbaum, J. B., & Mordatch, I. (2023) · arXiv · doi:10.48550/arxiv.2305.14325 · Cited by 96 · see citing works
Cognitive Architectures for Language Agents
Sumers, T. R., Yao, S., Narasimhan, K., & Griffiths, T. L. (2023) · arXiv · doi:10.48550/arxiv.2309.02427 · Cited by 72 · cited 1× · see citing works
“Single-agent systems exhibit high autonomy in task processing, with all information processing and operational logic concentrated within a single agent, making them suitable for handling relatively independent and singular tasks [6]–[9].”
MemGPT: Towards LLMs as Operating Systems
Packer, C., Wooders, S., Lin, K., Fang, V., Patil, S. G., Stoica, I., & Gonzalez, J. E. (2023) · arXiv · doi:10.48550/arxiv.2310.08560 · Cited by 64 · see citing works
TALM: Tool Augmented Language Models
Parisi, A., Zhao, Y., & Fiedel, N. (2022) · arXiv · doi:10.48550/arxiv.2205.12255 · Cited by 35 · see citing works
Mixture-of-Agents Enhances Large Language Model Capabilities
Wang, J., Wang, J., Athiwaratkun, B., Zhang, C., & Zou, J. (2024) · arXiv · doi:10.48550/arxiv.2406.04692 · Cited by 25 · see citing works
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Hu, C., Fu, J., Du, C., Luo, S., Zhao, J., & Zhao, H. (2023) · arXiv · doi:10.48550/arxiv.2306.03901 · Cited by 13 · see citing works
ToolCoder: Teach Code Generation Models to use API search tools
Zhang, K., Zhang, H., Li, G., Li, J., Li, Z., & Jin, Z. (2023) · arXiv · doi:10.48550/arxiv.2305.04032 · Cited by 12 · see citing works
Flagged first, then by citations
1 of the 17 references couldn’t be matched to a known paper.
Research works printed but not linked: 10
- Huang, 2024, Understanding the planning of 11m agents: A survey, arXiv preprint
- Han, 2024, LIm multi-agent systems: Challenges and open problems, arXiv preprint
- Li, 2023, Camel: Communicative agents for, mind” exploration of large language model society, 36, 51 991
- Wang, 2024, Megaagent: A practical framework for autonomous cooperation in large-scale 11m agent systems, arXiv preprint
- Zhang, 2023, Exploring collaboration mechanisms for 11m agents: A social psychology view, arXiv preprint
- Chen, 2023, Agentverse: Facilitating multi-agent col-laboration and exploring emergent behaviors in agents, arXiv preprint, 2, 6
- Liu, 2023, Dynamic 11m-agent network: An 11m-agent collaboration framework with agent team op-timization, arXiv preprint
- Liang, 2023, Unleashing infinite-length input capacity for large-scale language models with self-controlled memory system, arXiv e-prints, arXiv-2304
- Shao, 2023, Character-11m: A trainable agent for role-playing, arXiv preprint
- Mei, 2024, LIm agent operating system, arXiv preprint
Cited by
Sorted by citations
Fang, J., Peng, Y., Zhang, X., Wang, Y., Yi, X., Zhang, G., Xu, Y., Wu, B., Liu, S., Li, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.07407 · Cited by 6 · see citing works
MemIndex: Agentic Event-based Distributed Memory Management for Multi-agent Systems
Saleh, A., Tarkoma, S., Lindgren, A., Donta, P. K., Dustdar, S., Pirttikangas, S., & Lovén, L. (2025) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3774946 · Cited by 6 · see citing works
Towards Engineering LLM-Enhanced Multi-agent Systems: A Critical Examination of Roles
Asici, T. Z., Gürcan, Ö., & Kardaş, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-18011-7_12 · Cited by 3 · see citing works
RHLMA: A Role-Hierarchical LLM Multi-Agent Framework for Airborne Software Requirement Review
Sun, J., Yang, R., Gu, J., Chen, L., Zhao, Y., & Yang, X. (2026) · International Conference on Multi-scale Artificial Intelligence (MAI) · doi:10.1109/mai69289.2026.11543713
“Recent frameworks demonstrate that role-based, hierarchical workflows improve efficiency [6],[10],[11], a shift evidenced in aviation-specific applications for requirement standardization [12].”
EPIC: Accelerating Iterative Analytics in HPC Operations with Orchestrated Multi-Agent Systems
Karimi, A. M., Shin, W., Hines, J., Ghosal, T., Sattar, N. S., & Wang, F. (2026) · ISC High Performance (ISC) · doi:10.23919/isc.2026.11520478
Self-citation
- Authors
- Zou, H., Li, R., Sun, T., Wang, F., Li, T., & Liu, K.
- Affiliations
- Chongqing University (CN)
- Starkylin Research Develepment KylinSoft Co.,Ltd,ChangSha,China
- Chongqing Liangjiang Satellite Mobile Communication Co.,Ltd,Chongqing,China
- Venue
- 2024 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)
- Publisher
- IEEE
- Published
- 2024-10-25
- Pages
- 1-6
- OpenAlex
- W4404739821
- Semantic Scholar
- a4b97fdae96fd9b784a3fe9b3264af79be594fe5
- Cited by
- 4
- References
- 17
- Citations by year
- 2026: 3 · 2025: 1
- FWCI
- 1.18
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Keywords
- multi-agent systems, LLM agents, cooperative scheduling, hierarchical memory model, resource coordination, context window limitations, memory retention, resource contention
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
