International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Survey of Agentic AI and Multi-Agent LLM Systems for Intelligent Business Process Automation |
|---|---|
| ABSTRACT | Business process automation in small and mid-size firms still depends on Robotic Process Automation (RPA) bots and hand-written workflow rules, which stop working when an input format, a web page or a business rule changes. Large Language Model (LLM) agents that plan, call tools and work in teams offer another route. This paper surveys 43 works published between 2023 and 2026 on multi-agent LLM frameworks, reasoning and memory, tool use and agent protocols, LLM-driven workflow automation, agents for supply chain and retail operations, evaluation benchmarks, and governance and security. The works are arranged in a seven-part taxonomy and compared on coordination structure, tool access, human oversight, domain and reported results. Collaboration frameworks are well developed, but results on enterprise-style benchmarks are still modest: the best agent completes about 30% of tasks in a simulated software company, and a strong function-calling agent stays correct across eight repeated trials on fewer than 25% of retail customer-service tasks. Few systems combine multi-agent coordination, policy-based approval and an audit trail in one design, and almost none target small retailers whose staff work from mobile phones. Based on these findings, the paper outlines a reference architecture for retail process automation with a central orchestrator, four domain agents and a governance layer, and lists the open problems that remain. |
| AUTHOR | RAKSHE RUTUJA NAVNATH, RANPISE VIDYA VIKAS, SANDBHOR SALONI SAMBHAJI, PROF. JAGDALE S.V. UG Student, Dept. of Computer Engineering, SREIR's Samarth College of Engineering and Management, Belhe, Pune, Maharashtra, India Assistant Professor, Dept. of Computer Engineering, SREIR's Samarth College of Engineering and Management, Belhe, Pune, Maharashtra, India |
| VOLUME | 189 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1410035 |
| pdf/35_A Survey of Agentic AI and Multi-Agent LLM Systems for Intelligent Business Process Automation.pdf | |
| KEYWORDS | |
| References |
[1] M. Vidgof, S. Bachhofner and J. Mendling, "Large Language Models for Business Process Management: Opportunities and Challenges," in Business Process Management Forum (BPM 2023), Lecture Notes in Business Information Processing, Springer, 2023. [2] S. Yao, J. Zhao, D. Yu et al., "ReAct: Synergizing Reasoning and Acting in Language Models," in Proc. Int. Conf. on Learning Representations (ICLR), 2023. [3] T. Schick, J. Dwivedi-Yu, R. Dessi et al., "Toolformer: Language Models Can Teach Themselves to Use Tools," in Advances in Neural Information Processing Systems (NeurIPS), vol. 36, 2023. [4] L. Wang, C. Ma, X. Feng et al., "A Survey on Large Language Model based Autonomous Agents," Frontiers of Computer Science, vol. 18, no. 6, Art. 186345, 2024. [5] Z. Xi, W. Chen, X. Guo et al., "The Rise and Potential of Large Language Model Based Agents: A Survey," Science China Information Sciences, vol. 68, no. 2, Art. 121101, 2025. [6] Q. Wu, G. Bansal, J. Zhang et al., "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation," in Proc. Conf. on Language Modeling (COLM), 2024. [7] S. Hong, M. Zhuge, J. Chen, X. Zheng, Y. Cheng et al., "MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework," in Proc. Int. Conf. on Learning Representations (ICLR), 2024. [8] R. Sapkota, K. I. Roumeliotis and M. Karkee, "AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges," arXiv preprint arXiv:2505.10468, 2025. [9] T. Guo, X. Chen, Y. Wang et al., "Large Language Model based Multi-Agents: A Survey of Progress and Challenges," in Proc. 33rd Int. Joint Conf. on Artificial Intelligence (IJCAI), pp. 8048-8057, 2024. [10] K.-T. Tran, D. Dao, M.-D. Nguyen, Q.-V. Pham, B. O'Sullivan and H. D. Nguyen, "Multi-Agent Collaboration Mechanisms: A Survey of LLMs," arXiv preprint arXiv:2501.06322, 2025. [11] S. Raza, R. Sapkota, M. Karkee and C. Emmanouilidis, "TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems," arXiv preprint arXiv:2506.04133, 2025. [12] D. Calvanese, A. Casciani, G. De Giacomo, M. Dumas, F. Fournier, T. Kampik et al., "Agentic Business Process Management: A Research Manifesto," arXiv preprint arXiv:2603.18916, 2026. [13] Y. Ye, X. Cong, S. Tian, J. Cao, H. Wang, Y. Qin et al., "ProAgent: From Robotic Process Automation to Agentic Process Automation," arXiv preprint arXiv:2311.10751, 2023. [14] H. Vu, N. Klievtsova, H. Leopold, S. Rinderle-Ma and T. Kampik, "Agentic Business Process Management: Practitioner Perspectives on Agent Governance in Business Processes," arXiv preprint arXiv:2504.03693, 2025. [15] M. Dumas, F. Milani and D. Chapela-Campa, "Agentic Business Process Management Systems," arXiv preprint arXiv:2601.18833, 2026. [16] M. Azarijafari, L. Mich and M. Missikoff, "An Agentic AI for a New Paradigm in Business Process Development," arXiv preprint arXiv:2507.21823, 2025. [17] N. Shinn, F. Cassano, A. Gopinath, K. Narasimhan and S. Yao, "Reflexion: Language Agents with Verbal Reinforcement Learning," in Advances in Neural Information Processing Systems (NeurIPS), vol. 36, 2023. [18] J. S. Park, J. C. O'Brien, C. J. Cai, M. R. Morris, P. Liang and M. S. Bernstein, "Generative Agents: Interactive Simulacra of Human Behavior," in Proc. 36th ACM Symp. on User Interface Software and Technology (UIST), pp. 1-22, 2023. [19] C. Packer, S. Wooders, K. Lin et al., "MemGPT: Towards LLMs as Operating Systems," arXiv preprint arXiv:2310.08560, 2023. [20] Y. Qin, S. Liang, Y. Ye, K. Zhu, L. Yan, Y. Lu et al., "ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs," in Proc. Int. Conf. on Learning Representations (ICLR), 2024. [21] Y. Gao, Y. Xiong, X. Gao et al., "Retrieval-Augmented Generation for Large Language Models: A Survey," arXiv preprint arXiv:2312.10997, 2023. [22] G. Li, H. A. A. K. Hammoud, H. Itani, D. Khizbullin and B. Ghanem, "CAMEL: Communicative Agents for 'Mind' Exploration of Large Language Model Society," in Advances in Neural Information Processing Systems (NeurIPS), vol. 36, 2023. [23] C. Qian, W. Liu, H. Liu, N. Chen, Y. Dang, J. Li et al., "ChatDev: Communicative Agents for Software Development," in Proc. 62nd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 15174-15186, 2024. [24] W. Chen, Y. Su, J. Zuo, C. Yang, C. Yuan, C.-M. Chan et al., "AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors," in Proc. Int. Conf. on Learning Representations (ICLR), 2024. [25] Y. Du, S. Li, A. Torralba, J. B. Tenenbaum and I. Mordatch, "Improving Factuality and Reasoning in Language Models through Multiagent Debate," in Proc. 41st Int. Conf. on Machine Learning (ICML), 2024. [26] A. Fourney, G. Bansal, H. Mozannar, C. Tan, E. Salinas, E. Zhu et al., "Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks," arXiv preprint arXiv:2411.04468, 2024. [27] A. Singh, A. Ehtesham, S. Kumar and T. T. Khoei, "Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG," arXiv preprint arXiv:2501.09136, 2025. [28] A. Ehtesham, A. Singh, G. K. Gupta and S. Kumar, "A Survey of Agent Interoperability Protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)," arXiv preprint arXiv:2505.02279, 2025. [29] X. Hou, Y. Zhao, S. Wang and H. Wang, "Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions," arXiv preprint arXiv:2503.23278, 2025. [30] Z. Zeng, W. Watson, N. Cho et al., "FlowMind: Automatic Workflow Generation with LLMs," in Proc. 4th ACM Int. Conf. on AI in Finance (ICAIF), pp. 73-81, 2023. [31] M. Wornow, A. Narayan, K. Opsahl-Ong, Q. McIntyre, N. H. Shah and C. Re, "Automating the Enterprise with Foundation Models," arXiv preprint arXiv:2405.03710, 2024. [32] J. Zhang, J. Xiang, Z. Yu, F. Teng, X. Chen, J. Chen et al., "AFlow: Automating Agentic Workflow Generation," in Proc. Int. Conf. on Learning Representations (ICLR), 2025. [33] B. Li, K. Mellou, B. Zhang, J. Pathuri and I. Menache, "Large Language Models for Supply Chain Optimization," arXiv preprint arXiv:2307.03875, 2023. [34] Y. Quan and Z. Liu, "InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains," arXiv preprint arXiv:2407.11384, 2024. [35] V. Jannelli, S. Schoepf, M. Bickel, T. Netland and A. Brintrup, "Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking," arXiv preprint arXiv:2411.10184, 2024. [36] Y. Qi, J. Yin, J. Zhang et al., "Leveraging LLM-Based Agents for Intelligent Supply Chain Planning," arXiv preprint arXiv:2509.03811, 2025. [37] K. Yoshizato, K. Shimizu, R. Higa and T. Otsuka, "AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval," arXiv preprint arXiv:2602.05524, 2026. [38] S. Yao, N. Shinn, P. Razavi and K. Narasimhan, "tau-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains," in Proc. Int. Conf. on Learning Representations (ICLR), 2025. [39] X. Liu, H. Yu, H. Zhang, Y. Xu, X. Lei, H. Lai et al., "AgentBench: Evaluating LLMs as Agents," in Proc. Int. Conf. on Learning Representations (ICLR), 2024. [40] A. Drouin, M. Gasse, M. Caccia, I. H. Laradji, M. Del Verme, T. Marty et al., "WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?," in Proc. 41st Int. Conf. on Machine Learning (ICML), 2024. [41] F. F. Xu, Y. Song, B. Li, Y. Tang, K. Jain, M. Bao et al., "TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks," in Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2025. [42] M. Cemri, M. Z. Pan, S. Yang et al., "Why Do Multi-Agent LLM Systems Fail?," arXiv preprint arXiv:2503.13657, 2025. [43] K. Greshake, S. Abdelnabi, S. Mishra, C. Endres, T. Holz and M. Fritz, "Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection," in Proc. 16th ACM Workshop on Artificial Intelligence and Security (AISec), pp. 79-90, 2023. |