AGENTIC LARGE LANGUAGE MODELS: A SYSTEMATIC REVIEW OF ARCHITECTURES, REASONING, AND MULTI-AGENT COLLABORATION

Muhammad Awais; Muhammad Ayaz

doi:10.67809/ijetrm.1789357569

Abstract

Agentic large language models (LLMs)—systems that couple a foundation model with an execution loop for
perception, planning, memory, tool use, and multi-step action—have moved from research prototypes to widely
deployed infrastructure since 2022. This review synthesizes the 2023–2026 literature on agentic LLMs across
four dimensions: architectures (single- and multi-agent, monolithic and modular), reasoning and planning
(chain-of-thought, ReAct, Tree-of-Thoughts, and reflection-based self-correction), tool use (function calling,
retrieval, and post-execution verification), and multi-agent collaboration (centralized, decentralized, and
hierarchical coordination). Using a review protocol modeled on PRISMA guidance, we screened literature from
arXiv, ACL/ICLR/NeurIPS proceedings, and primary industry technical reports, applying explicit inclusion and
exclusion criteria and developing a structured taxonomy through iterative coding of fifty primary sources. We
synthesize empirical evidence on when multi-agent systems outperform single agents—and when they do not:
large-scale failure analyses find that coordination and verification failures, rather than base-model capability
alone, account for the majority of multi-agent task failures. We map the benchmark landscape (GAIA, SWEbench, WebArena, AgentBench) and emerging “time-horizon” metrics that track rapid, measurable growth in
the length of tasks agents can complete autonomously. We then examine open challenges in reliability, safety,
and governance before turning to the technical and policy levers—compute, full-stack export strategy, standards
leadership, and talent—most relevant to sustaining U.S. leadership in agentic artificial intelligence amid
intensifying international competition. We close with a forward-looking research agenda spanning verifiable
evaluation, self-improving systems, and multi-agent security.

Keywords

Agentic AI; large language model agents; multi-agent systems; tool use; reasoning and planning; benchmark

References

1) Anthropic. (2024).Introducing the Model Context Protocol. Anthropic Engineering Blog.
2) Anthropic. (2025a).How we built our multi-agent research system. Anthropic Engineering Blog.
3) Anthropic. (2025b).Building effective agents. Anthropic Research.
4) Brohan, A., Brown, N., Carbajal, J., Chebotar, Y., Chen, X., Choromanski, K., Ding, T., Driess, D.,
Dubey, A., Finn, C., Florence, P., Fu, C., Arenas, M. G., Gopalakrishnan, K., Han, K., Hausman, K.,
Herzog, A., Hsu, J., Ibarz, J., … Zitkovich, B. (2023).
RT-2: Vision-language-action models transfer web knowledge to robotic control. arXiv:2307.15818.
5) Bureau of Industry and Security, U.S. Department of Commerce. (2025).
Export administration regulations: Advanced computing and semiconductor manufacturing items.
6) Cemri, M., Pan, M. Z., Yang, S., Agrawal, L. A., Chopra, B., Tiwari, R., Keutzer, K., Parameswaran,
A., Klein, D., Ramchandran, K., Zaharia, M., Gonzalez, J. E., & Stoica, I. (2025).
Why do multi-agent LLM systems fail? arXiv:2503.13657.
7) Chen, W., Su, Y., Zuo, J., Yang, C., Yuan, C., Chan, C.-M., Yu, H., Lu, Y., Hung, Y.-H., Qian, C.,
Qin, Y., Cong, X., Xie, R., Liu, Z., Sun, M., & Zhou, J. (2024).
AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors. Proceedings of
ICLR 2024.
8) Chhikara, P., Khant, D., Aryan, S., Singh, T., & Yadav, D. (2025).
Mem0: Building production-ready AI agents with scalable long-term memory. arXiv:2504.19413.
9) CrewAI, Inc. (2024).CrewAI: Framework for orchestrating role-playing, autonomous AI agents.
crewai.com.
10) Du, Y., Li, S., Torralba, A., Tenenbaum, J. B., & Mordatch, I. (2023).
Improving factuality and reasoning in language models through multiagent debate. arXiv:2305.14325.
11) Executive Office of the President. (2025).
America’s AI Action Plan. The White House.
12) Fourney, A., Bansal, G., Mozannar, H., Tan, C., Salinas, E., Niedtner, F., Proebsting, G., Bassman, G.,
Gerrits, J., Alber, J., Chang, P., Chawla, R., Ghelfi, R., Sibue, M., Sokolov, A., Vijayvargiya, S.,
White, R., & Amershi, S. (2024).
Magentic-One: A generalist multi-agent system for solving complex tasks. arXiv:2411.04468.
13) Gottweis, J., Weng, W.-H., Daryin, A., Tu, T., Palepu, A., Sirkovic, P., Myaskovsky, A.,
Weissenberger, F., Rong, K., Tanno, R., Saab, K., Popovici, D., Blum, J., Zhang, F., Chou, K.,
Hassidim, A., Gokturk, B., Vahdat, A., Kohli, P., … Natarajan, V. (2025).
Towards an AI co-scientist. arXiv:2502.18864.
14) Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024).
Large language model based multi-agents: A survey of progress and challenges. arXiv:2402.01680.
15) Hammond, L., Chan, A., Clifton, J., Hoelscher-Obermaier, J., Khan, A., McLean, E., Smith, C.,
Barfuss, W., Foerster, J., Gavenciak, T., Han, T. A., Hughes, E., Kovarik, V., Kulveit, J., Leibo, J. Z.,
Oesterheld, C., de Witt, C. S., Shah, N., Wellman, M., … Rahwan, I. (2025).
Multi-agent risks from advanced AI. Cooperative AI Foundation, Technical Report #1.
arXiv:2502.14143.
16) Han, S., Zhang, Q., Yao, Y., Jin, W., Xu, Z., & He, C. (2024). LLM multi-agent systems: Challenges
and open problems. arXiv:2402.03578.
17) Hong, S., Zheng, X., Chen, J., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S. K. S., Lin, Z., Zhou,
L., Ran, C., Xiao, L., Wu, C., & Schmidhuber, J. (2024).
MetaGPT: Meta programming for a multi-agent collaborative framework. Proceedings of ICLR 2024.
18) Huang, Y., Shi, J., Li, Y., Fan, C., Wu, S., Zhang, Q., Liu, Y., Zhou, P., Wan, Y., Gong, N. Z., & Sun,
L. (2023). MetaTool benchmark for large language models: Deciding whether to use tools and which to
use. arXiv:2310.03128.
19) Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. R. (2024).
SWE-bench: Can language models resolve real-world GitHub issues? Proceedings of ICLR 2024.
20) Kapoor, S., Stroebl, B., Siegel, Z. S., Nadgir, N., & Narayanan, A. (2024).
AI agents that matter. arXiv:2407.01502.
21) Kwa, T., West, B., Becker, J., Deng, A., Garcia, K., Hasin, M., Jawhar, S., Kinniment, M., Rush, N.,
Arx, S. V., Bloom, R., Broadley, T., Du, H., Goodrich, B., Hasin, N., Ho, L., Jacob, A., Kutasov, D.,
Lin, T., … Barnes, E. (2025). Measuring AI ability to complete long software tasks. METR.
arXiv:2503.14499.
22) LangChain, Inc. (2024). LangGraph: Building stateful, multi-actor applications with LLMs.
langchain.com.
23) Li, M., Zhao, Y., Yu, B., Song, F., Li, H., Yu, H., Li, Z., Huang, F., & Li, Y. (2023a).
API-Bank: A comprehensive benchmark for tool-augmented LLMs. Proceedings of EMNLP 2023.
24) Li, G., Hammoud, H. A. A. K., Itani, H., Khizbullin, D., & Ghanem, B. (2023b).
CAMEL: Communicative agents for “mind” exploration of large language model society. Proceedings
of NeurIPS 2023.
25) Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., Zhang, S.,
Deng, X., Zeng, A., Du, Z., Zhang, C., Shen, S., Zhang, T., Su, Y., Sun, H., … Tang, J. (2023).
AgentBench: Evaluating LLMs as agents. arXiv:2308.03688.
26) Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N.,
Prabhumoye, S., Yang, Y., Gupta, S., Majumder, B. P., Hermann, K., Welleck, S., Yazdanbakhsh, A.,
& Clark, P. (2023).
Self-Refine: Iterative refinement with self-feedback. Proceedings of NeurIPS 2023.
27) METR. (2026). Time Horizon 1.1: Updated measurements of AI task-completion capability. METR
technical update.
28) Mialon, G., Fourrier, C., Swift, C., Wolf, T., LeCun, Y., & Scialom, T. (2023).
GAIA: A benchmark for general AI assistants. arXiv:2311.12983.
29) Packer, C., Wooders, S., Lin, K., Fang, V., Patil, S. G., Stoica, I., & Gonzalez, J. E. (2024).
MemGPT: Towards LLMs as operating systems. arXiv:2310.08560.
30) Park, J. S., O’Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023).
Generative agents: Interactive simulacra of human behavior. Proceedings of UIST 2023.
31) Patil, S. G., Zhang, T., Wang, X., & Gonzalez, J. E. (2023).
Gorilla: Large language model connected with massive APIs. arXiv:2305.15334.
32) Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li,
D., Liu, Z., & Sun, M. (2024).
ChatDev: Communicative agents for software development. Proceedings of ACL 2024.
33) Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., Zhao, S.,
Hong, L., Tian, R., Xie, R., Zhou, J., Gerstein, M., Li, D., Liu, Z., & Sun, M. (2023).
ToolLLM: Facilitating large language models to master 16000+ real-world APIs. arXiv:2307.16789.
34) Rasmussen, P., Paliychuk, P., Beauvais, T., Ryan, J., & Chalef, D. (2025).
Zep: A temporal knowledge graph architecture for agent memory. arXiv:2501.13956.
35) Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L.,
Cancedda, N., & Scialom, T. (2023).
Toolformer: Language models can teach themselves to use tools. Proceedings of NeurIPS 2023.
36) Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., & Yao, S. (2023).
Reflexion: Language agents with verbal reinforcement learning. Proceedings of NeurIPS 2023.
37) Surapaneni, R., Jha, M., Vakoc, M., & Segal, T. (2025).
A2A: A new era of agent interoperability. Google Developers Blog.
38) Trivedi, H., Khot, T., Hartmann, M., Manku, R., Dong, V., Li, E., Gupta, S., Sabharwal, A., &
Balasubramanian, N. (2024).
AppWorld: A controllable world of apps and people for benchmarking interactive coding agents.
Proceedings of ACL 2024.
39) Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., & Anandkumar, A. (2023).
Voyager: An open-ended embodied agent with large language models. arXiv:2305.16291.
40) Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y.,
Zhao, W. X., Wei, Z., & Wen, J. (2024).
A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6),
186345.
41) Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022).
Chain-of-thought prompting elicits reasoning in large language models. Proceedings of NeurIPS 2022.
42) Wu, Q., Bansal, G., Zhang, J., Wu, Y., Zhang, S., Zhu, E., Li, B., Jiang, L., Zhang, X., & Wang, C.
(2024).
AutoGen: Enabling next-gen LLM applications via multi-agent conversation. Proceedings of COLM
2024.
43) Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., Zheng,
R., Fan, X., Wang, X., Xiong, L., Zhou, Y., Wang, W., Jiang, C., Zou, Y., Liu, X., … Gui, T. (2024).
The rise and potential of large language model based agents: A survey. arXiv:2309.07864.
44) Xu, W., Liang, Z., Mei, K., Gao, H., Tan, J., & Zhang, Y. (2025).
A-Mem: Agentic memory for LLM agents. arXiv:2502.12110.
45) Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023a).
ReAct: Synergizing reasoning and acting in language models. Proceedings of ICLR 2023.
46) Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023b).
Tree of Thoughts: Deliberate problem solving with large language models. Proceedings of NeurIPS
2023.
47) Zhong, W., Guo, L., Gao, Q., Ye, H., & Wang, Y. (2024). MemoryBank: Enhancing large language
models with long-term memory. Proceedings of AAAI 2024.
48) Zhou, S., Xu, F. F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y., Fried, D., Alon,
U., & Neubig, G. (2024).
WebArena: A realistic web environment for building autonomous agents. Proceedings of ICLR 2024.
49) Ali, Y., Ayaz, M., Baig, U., & Awais, M. (2025). A novel analytical framework for handling massive
distributed energy participants using Prosumers Web. 2025 International Conference on Engineering &
Computing Technologies (ICECT).
50) Ali, Y., Ayaz, M., Khan, K., Biswas, A. K., & Baig, U. (2025). Prosumer Web City: A novel energy
market framework for enabling dynamic bidding and scalable integration of distributed energy
participants. Scientific Reports, 16(1), 1080.
51) Arsalan, M., Ayaz, M., Ali, Y., & Baig, U. (2025). AI-enabled energy load forecasting for smart grid
management. International Journal of Scientific Research and Engineering Development, 8(6).
52) Arsalan, M., Ayaz, M., Ali, Y., & Baig, U. (2025). Integrating AI-driven decision systems in electrical
engineering project management. International Journal of Scientific Research and Engineering
Development, 8.
53) Arsalan, M., Ayaz, M., Ali, Y., & Baig, U. (2025). Secure and scalable cloud architectures for
connected vehicle ecosystems. International Journal of Scientific Research and Engineering
Development, 8.
54) Awais, M., & Ayaz, M. (2026). Artificial intelligence for strengthening national cybersecurity:
Advanced threat detection and automated response systems. International Journal of Engineering
Technology Research & Management, 10(08).
55) Ayaz, M., Baig, D.-e.-Z., Hur Rizvi, S. M., Alharbi, S. S., Iqbal, S., & Shafiullah, M. (2025).
Automatic generation control optimization for power system resilience under real world load variations
using genetic algorithm. Scientific Reports, 15(1), 20857.
56) Ayaz, M., Baig, U., & Awais, M. (2025). Enhancing power grid resilience with adaptive ANN-based
voltage control strategies. 2025 International Conference on Emerging Technologies in Electronics.
57) Ayaz, M., Baig, U., Dawood, M., & Awais, M. (2025).
Optimizing voltage control in power systems: An artificial neural network approach for improved
performance and stability. 2025 International Conference on Emerging Power Technologies (ICEPT),
1–6.
58) Ayaz, M., Mehmood, F., Ali, Y., Ahmad, U., Baig, U., & Awais, M. (n.d.). Resilient AI-driven
adaptive neuro-fuzzy inference system control of boost converters.
59) Ayaz, M., Rizvi, S. M. H., & Akbar, M. (2023). Dynamic power factor correction in industrial systems:
An automated capacitor bank control approach. 2023 2nd International Conference on Emerging
Trends in Electrical, Control and Telecommunication Engineering.
60) Ayaz, M., Rizvi, S. M. H., & Akbar, M. (2024). Conservation voltage reduction impact investigation
for personal computing devices using experimental measurements and computation performance
metrics. Metrology, 4(1), 24–45.
61) Ayaz, M., Rizvi, S. M. H., & Akbar, M. (2024). Probabilistic CVR assessment in distribution networks
using synthetic consumption database of household appliances. Arabian Journal for Science and
Engineering, 49(12), 16889–16901.
62) Ayaz, M., Rizvi, S. M. H., Ejaz, S., Haq, M. A. U., & Rathi, L. (2024). Advanced power system
optimization: Evaluation of automatic generation control techniques in two-area networks. 2024 21st
International Bhurban Conference on Applied Sciences and Technology (IBCAST).
63) Ayaz, M., Rizvi, S. M. H., Rathi, L., Haq, M. A. U., & Ejaz, S. (2024). Machine learning based robust
control solutions for buck converters: ANN and fuzzy logic methods. 2024 21st International Bhurban
Conference on Applied Sciences and Technology (IBCAST).
64) Ayaz, M., Shah, S. W. H., Asif, H. B., & Haq, M. A. U. (2024). Integrated distributed generation for
practical implementation of urban lighting using hybrid renewable energy. 2024 4th International
Conference on Digital Futures and Transformative Technologies.
65) Baig, U., Ayaz, M., & Baig, D.-e.-Z. (2025). Advanced time-frequency analysis for fault detection and
classification in power transmission systems using wavelet transform. Proceedings of the International
Conference on Emerging Power Technologies (ICEPT), 1–6.
66) Bano, F., & Ayaz, M. (2025). Resilient ANFIS framework for robust boost converter stability in real
world conditions. IEEE Access.
67) Bano, F., Ayaz, M., Baig, D.-e.-Z., & Rizvi, S. M. H. (2024). Intelligent control algorithms for
enhanced frequency stability in single and interconnected power systems. Electronics, 13(21), 4219.
68) Ejaz, S., Ayaz, M., Dawood, M., Haq, M. A. U., & Rathi, L. (2024). Impact of load variations on the
stability of GA-optimized PID controllers in isolated power systems. 2024 19th International
Conference on Emerging Technologies (ICET), 1–6.
69) Faheem, M., Awais, M., Iqbal, A., & Zia, H. (2025). Adaptive AI-driven cyber threat detection system
for US critical infrastructure protection. World Journal of Advanced Research and Reviews, 26(3),
2282–2291.
70) Faheem, M., Awais, M., Iqbal, A., & Zia, H. (2025). AI-augmented cybersecurity for smart grids in the
United States. World Journal of Advanced Research and Reviews, 7(1), 713–726.
71) Faheem, M., Awais, M., Iqbal, A., & Zia, H. (2025). Enhancing IT incident management with natural
language processing and predictive analytics. International Journal of Science and Research Archive,
15(3), 224–237.
72) Faheem, M., Awais, M., Iqbal, A., & Zia, H. (2025). Neural infrastructure: A federated AI framework
for predictive resilience in US transportation systems.
73) Haq, M. A. U., Ayaz, M., Asif, H. B., & Shah, S. W. H. (2024). Integrating machine learning with
variable frequency drive for enhanced speed control in induction motors. 2024 International
Conference on Engineering & Computing Technologies (ICECT).
74) Rathi, L., Ayaz, M., Ejaz, S., Dawood, M., & Haq, M. A. U. (2024).Evaluation of predictive and
heuristic control techniques for buck converters using MPC, PID, and fuzzy logic. 2024 26th
International Multi-Topic Conference (INMIC), 1–6.
75) Rizvi, S. M. H., Satti, S. G., & Ayaz, M. (2024). Supervised learning framework for identification of
inverter control mode and estimation of inverter-based-resource & load parameters. IEEE Transactions
on Industry Applications, 61(2), 2846–2857.