Design and Application of Autonomous Decision-Making Systems Based on AI Agents

Article Sidebar

PDF
Published: 06.09.2026

Main Article Content

Babayev Mahammad Murad
Baku Higher Oil School

Abstract

The rapid development of large language models and tool-enabled artificial intelligence has shifted attention from systems that only generate responses toward agents that can perceive a task, plan a sequence of actions, use external tools, evaluate intermediate results and adapt their behavior. This transition creates new opportunities for autonomous decision-making, but it also introduces engineering problems related to planning reliability, memory, tool selection, uncertainty, safety and human control. This article examines the design and practical application of autonomous decision-making systems based on AI agents. A design-oriented analytical approach is used to synthesize recent research on single-agent and multi-agent architectures, collaborative reasoning, online planning, human-agent interaction and agent evaluation. On this basis, an Agent-Based Autonomous Decision Architecture (AADA) is proposed. The architecture organizes decision-making into eight stages: perception, goal interpretation, context retrieval, option generation, evaluation, action selection, execution and feedback-based updating.

Downloads

Download data is not yet available.

Article Details

Data Availability Statement

All data supporting the findings of this study are presented in the text of the scientific work.

Issue

No. 308 (2026): 8th ISPC «Progressive Science and Achievements» (September 6-8, 2026; Dallas, USA).

Section

Information and Web technologies
Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Biography

Babayev Mahammad Murad, Baku Higher Oil School

Undergraduate Student in Computer Engineering

How to Cite

Babayev, M. (2026). Design and Application of Autonomous Decision-Making Systems Based on AI Agents. Scientific Collection «InterConf», 308, 117–122. https://interconf.openpubarchive.com/index.php/proceeding/article/view/85

References

Feng, X., Chen, Z.-Y., Qin, Y., Lin, Y., Chen, X., Liu, Z., & Wen, J.-R. (2024). Large Language Model -based Human-Agent Collaboration for Complex Task Solving. Findings of the Association for Computational Linguistics: EMNLP 2024, 1336-1357.

Chen, P., Zhang, S., & Han, B. (2024). CoMM: Collaborative Multi - Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving. Findings of the Association for Computational Linguistics: NAACL 2024, 1720-1738.

Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., & Tu, Z. (2024). Encouraging Divergent Thinking in Large Language Models through Multi -Agent Debate. Proceedings of EMNLP 2024, 17889-17904.

Zhao, X., Wang, K., & Peng, W. (2024). An Electoral Approach to Diversify LLM -based Multi -Agent Collective Decision -Making. Proceedings of EMNLP 2024, 2712-2727.

Zhou, W., Mesgar, M., Friedrich, A., & Adel, H. (2025). Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering. Findings of the Association for Computational Linguistics: NAACL 2025, 945-968.

Tang, J., Shen, S., Wang, Z., Gong, Z., Feng, X., Sun, Z., Tan, H., & Chen, X. (2025). KAPA: A Deliberative Agent Framework with Tree - Structured Knowledge Base for Multi-Domain User Intent Understanding. Findings of the Association for Computational Linguistics: ACL 2025, 6150-6166.

Zhou, H., Geng, H., Xue, X., Kang, L., Qin, Y., Wang, Z., Yin, Z., & Bai, L. (2025). ReSo: A Reward -driven Self -organizing LLM -based Multi-Agent System for Reasoning Tasks. Proceedings of EMNLP 2025, 15979-15998.

Wang, Y., Liu, S., Fang, J., & Meng, Z. (2025). EvoAgentX: An Automated Framework for Evolving Agentic Workflows. Proceedings of EMNLP 2025: System Demonstrations, 643-655.