Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Artificial Intelligence Practice
  4. Vol 9, Issue 1, 2026

Research on a Multi-SOP Interruption–Resumption Agentic Algorithm for Complex Business Workflows

Download as PDF

DOI: 10.23977/jaip.2026.090117 | Downloads: 0 | Views: 65

Author(s)

Zhenggang Wei 1, Jinbin Xu 1, Zelin Zheng 1, Xialin Zhang 1, Haichao Gao 1

Affiliation(s)

1 Ping An Jin Guan Jia Development Team, Ping An Life Insurance Company of China, Ltd., Shenzhen, China

Corresponding Author

Xialin Zhang

ABSTRACT

In complex business scenarios, a customer will often switch quickly among multiple SOPs. The challenge for traditional intelligent customer service systems is that they do not provide the ability to remove siloed information, retain state, and allow for intelligent recovery after interruptions when processing multiple SOPs, requiring users to restart their workflows again from the beginning. In this paper, we will describe an agentic algorithm based on a multi-SOP agentic interruption/resumption perspective. The framework consists of three core capabilities: First, dual-state decoupling separates nondeterministic cognitive decision-making (Coordinator Agent) from deterministic business execution via stateless SOP tools, reducing orchestration complexity and computational overhead. Second, a six-tuple Global State Container serves as the single source of truth for cross-SOP information transfer, enabling automatic reuse of critical business entities and silent propagation of prerequisite parameters across heterogeneous workflows. Third, a Diff Reasoning mechanism measures state discrepancies between frozen snapshots and current global memory, dynamically selecting lossless recovery or safe rollback paths to prevent semantic rollback attacks. The multi-SOP framework reduced the need for users to input the same information more than once, resulting in an 85% reduction to only 12.3, a cross-SOP recovery success rate of 96.3%, and a 73.5% successful chained task completion rate. Average end -to-end time to completion for the multi-SOP framework was also improved by 52.4% (24.6 minutes to 11.7 minutes). Finally, the overall user satisfaction score increased from 2.8 to 4.5.

KEYWORDS

Multi-SOP Collaboration, Global State Awareness, Diff Reasoning, Dual-State Decoupling, Checkpoint Continuity

CITE THIS PAPER

Zhenggang Wei, Jinbin Xu, Zelin Zheng, Xialin Zhang, Haichao Gao. Research on a Multi-SOP Interruption–Resumption Agentic Algorithm for Complex Business Workflows. Journal of Artificial Intelligence Practice (2026). Vol. 9, No. 1, 150-166. DOI: http://dx.doi.org/10.23977/jaip.2026.090117.

REFERENCES

[1] Wang L, Ma C, Feng X, et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science, 2024, 18(6): 186345.
[2] Li G, Hammoud H, Itani H, et al. Camel: Communicative agents for" mind" exploration of large language model society[J]. Advances in neural information processing systems, 2023, 36: 51991-52008.
[3] Romero O J, Zimmerman J, Steinfeld A, et al. Synergistic integration of large language models and cognitive architectures for robust AI: an exploratory analysis[J]. Proceedings of the AAAI Symposium Series, 2024, 2(1): 396-405.
[4] Hatalis K, Christou D, Myers J, et al. Memory matters: The need to improve long-term memory in LLM-agents[C]//Proceedings of the AAAI Symposium Series. 2024, 2(1): 277-280.
[5] Hu M, Chen T, Chen Q, et al. Hiagent: Hierarchical working memory management for solving long-horizon agent tasks with large language model[C]//Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025: 32779-32798.
[6] Gao P, Zhao J, Chen X, et al. An efficient context-dependent memory framework for llm-centric agents[C]//Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track). 2025: 1055-1069.
[7] Qin Y, Liang S, Ye Y, et al. Toolllm: Facilitating large language models to master 16000+ real-world apis[C]//International Conference on Learning Representations. 2024, 2024: 9695-9717.
[8] Ma C, Zhang J, Zhu Z, et al. Agentboard: An analytical evaluation board of multi-turn llm agents[J]. Advances in neural information processing systems, 2024, 37: 74325-74362.
[9] Reimann M M, Kunneman F A, Oertel C, et al. A survey on dialogue management in human-robot interaction[J]. ACM Transactions on Human-Robot Interaction, 2024, 13(2): 1-22.
[10] Zhang X, Dong X, Wang Y, et al. A survey of multi-ai agent collaboration: Theories, technologies and applications[C]//Proceedings of the 2nd Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence. 2025: 1875-1881.
[11] Sumers T R, Yao S, Narasimhan K, et al. Cognitive architectures for language agents[J]. Transactions on Machine Learning Research, 2024.
[12] Zhang Z, Dai Q, Bo X, et al. A survey on the memory mechanism of large language model based agents[J]. ACM Transactions on Information Systems, 2025, 43(6): 1-47.
[13] Liu X, Yu H, Zhang H, et al. Agentbench: Evaluating llms as agents[C]//International Conference on Learning Representations. 2024, 2024: 52989-53046.
[14] Xie T, Zhang D, Chen J, et al. Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments[J]. Advances in Neural Information Processing Systems, 2024, 37: 52040-52094.
[15] Shinn N, Cassano F, Gopinath A, et al. Reflexion: Language agents with verbal reinforcement learning[J]. Advances in neural information processing systems, 2023, 36: 8634-8652.
[16] Chen Z, Xiang Z, Xiao C, et al. Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases[J]. Advances in Neural Information Processing Systems, 2024, 37: 130185-130213.
[17] Zhao A, Huang D, Xu Q, et al. Expel: Llm agents are experiential learners[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(17): 19632-19642.
[18] Xie J, Zhang K, Chen J, et al. Travelplanner: A benchmark for real-world planning with language agents[J]. arXiv preprint arXiv:2402.01622, 2024.
[19] Nau D S, Au T C, Ilghami O, et al. SHOP2: An HTN planning system[J]. Journal of Artificial Intelligence Research, 2003, 20: 379-404.
[20] Sun C, Huang S, Pompili D. LLM-based multi-agent decision-making: challenges and future directions[J]. IEEE Robotics and Automation Letters, 2025, 10(6): 5681-5688.
[21] LangChain. LangGraph: Stateful, graph-based orchestration for LLM agents[EB/OL]. https://github.com/langchain-ai/langgraph, 2024.
[22] Xi Z, Chen W, Guo X, et al. The rise and potential of large language model based agents: A survey[J]. Science China Information Sciences, 2025, 68(2): 121101.
[23] Zheng J, Qiu S, Shi C, et al. Towards lifelong learning of large language models: A survey[J]. ACM Computing Surveys, 2025, 57(8): 1-35.
[24] Croissant M, Frister M, Schofield G, et al. An appraisal-based chain-of-emotion architecture for affective language model game agents[ J] . PLOS ONE, 2024, 19( 5): e0301033.
[25] Wu D, Wang H, Yu W, et al. Longmemeval: Benchmarking chat assistants on long-term interactive memory[J]. arXiv preprint arXiv:2410.10813, 2024.
[26] Xu X, Gou Z, Wu W, et al. Long time no see! open-domain conversation with long-term persona memory[C]//Findings of the Association for Computational Linguistics: ACL 2022. 2022: 2639-2650.
[27] Portugal I D S, Alencar P, Cowan D. An agentic AI-based multi-agent framework for recommender systems[C]//2024 IEEE International Conference on Big Data (BigData). IEEE, 2024: 5375-5382.
[28] Lim J, Vogel-Heuser B, Kovalenko I. Large language model-enabled multi-agent manufacturing systems[C]//2024 IEEE 20th International Conference on Automation Science and Engineering (CASE). IEEE, 2024: 3940-3946.
[29] Hong S, Zhuge M, Chen J, et al. MetaGPT: Meta programming for a multi-agent collaborative framework[C]//International Conference on Learning Representations. 2024, 2024: 23247-23275.
[30] Park J S, O'Brien J, Cai C J, et al. Generative agents: Interactive simulacra of human behavior[C]//Proceedings of the 36th annual acm symposium on user interface software and technology. 2023: 1-22.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 26675
Visits: 840102

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.