Research on AI agents in economics and computer science: Thematic areas, dynamics, and prospects
Abstract
This article presents a systematized review of academic publications on autonomous AI agents, based on the analysis of 1,634 works from international peer-reviewed journals indexed in the Scopus database. Using thematic modeling with contextualized embeddings via BERTopic, the study identifies key research directions on AI agents within computer science as well as their applications in the social sciences. Thirteen major thematic areas are distinguished and grouped into the following broader categories: interaction and communication of AI agents, applied use of AI agents, ethics and trust in AI agents, and the learnability and adaptability of AI agents. The review highlights a growing interest in the study of human-AI agent interaction and reveals a thematic evolution from formal planning models toward the integration of large language models and self-learning systems. The analysis also points to the dominance of U.S.-based organizations in the volume of published research, alongside the rapid development of this field in China, with all other countries significantly lagging behind. The article concludes by outlining promising research directions, including the coordination of heterogeneous agents under uncertainty and the assessment of the socio-technical implications of their deployment.
Acknowledgments
The study was supported by the Russian Science Foundation, grant No. 25-18-00539, https://rscf.ru/project/25-18-00539/
Downloads
References
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026). AI Agents vs. Agentic AI: A conceptual taxonomy, applications and challenges. Information Fusion, 126(B), 103599. https://doi.org/10.1016/j.inffus.2025.103599
Chi, O. H., Denton, G., & Gursoy, D. (2020). Artificially intelligent device use in service delivery: A systematic review, synthesis, and research agenda. Journal of Hospitality Marketing & Management, 29(7), 757–786. https://doi.org/10.1080/19368623.2020.1721394
Ferrag, M. A., Tihanyi, N., & Debbah, M. (2025). From LLM reasoning to autonomous AI agents: A comprehensive review. arXiv:2504.19678. https://doi.org/10.48550/arXiv.2504.19678
Wang, Q., Jing, S., & Goel, A. K. (2022). Co-designing AI agents to support social connectedness among online learners: Functionalities, social characteristics, and ethical challenges. Proceedings of the 2022 ACM Designing Interactive Systems Conference, 541–556. https://doi.org/10.1145/3532106.3533534
Hong, J.-W., Cho, S., & Williams, D. (2020). Sexist AI: An experiment integrating CASA and ELM. International Journal of Human–Computer Interaction, 36(20), 1928–1941. https://doi.org/10.1080/10447318.2020.1801226
Mehrotra, S., Jorge, C. C., Jonker, C. M., & Tielman, M. L. (2024). Integrity-based explanations for fostering appropriate trust in AI agents. ACM Transactions on Interactive Intelligent Systems, 14(1), 4. https://doi.org/10.1145/3610578
Dushkin, R. V. (2019). Razvitiye metodov adaptivnogo obucheniya pri pomoshchi ispol'zovaniya intellektual'nykh agentov [Development of adaptive teaching methods using intelligent agents]. Iskusstvenniy Intellekt i Prinyatie Resheniy [Artificial Intelligence and Decision Making], (1), 87–96 (in Russian). https://doi.org/10.14357/20718594190108
Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv:2203.05794. https://doi.org/10.48550/arXiv.2203.05794
Galli, C., Donos, N., & Calciolari, E. (2024). Performance of 4 pre-trained sentence transformer models in the semantic query of a systematic review dataset on peri-implantitis. Information, 15(2), 68. https://doi.org/10.3390/info15020068
Ponnusamy, P., Roshan Ghias, A., Guo, C., & Sarikaya, R. (2020). Feedback-based self-learning in large-scale conversational AI agents. Proceedings of the AAAI Conference on Artificial Intelligence, 34(08), 13180–13187. https://doi.org/10.1609/aaai.v34i08.7022
Zhang, C., Yang, K., Hu, S., Wang, Z., Li, G., Sun, Y., … Yang, Y. (2024). ProAgent: Building proactive cooperative agents with large language models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17591–17599. https://doi.org/10.1609/aaai.v38i16.29710
Mari, A., Mandelli, A., & Algesheimer, R. (2024). Empathic voice assistants: Enhancing consumer responses in voice commerce. Journal of Business Research, 175, 114566. https://doi.org/10.1016/j.jbusres.2024.114566
Choi, S., & Zhou, J. (2023). Inducing consumers’ self-disclosure through the fit between Chatbot’s interaction styles and regulatory focus. Journal of Business Research, 166, 114127. https://doi.org/10.1016/j.jbusres.2023.114127
Park, S., Choi, W. J., & Shin, D. (2021). Who makes you more disappointed? The effect of avatar presentation, company market status, and agent identity on customers’ perceived service quality and satisfaction of online chatting services. Asia Marketing Journal, 23(3), 4. https://doi.org/10.53728/2765-6500.1577
Wu, S., Fei, H., Qu, L., Ji, W., & Chua, T.-S. (2023). NExT-GPT: Any-to-any multimodal LLM. arXiv:2309.05519. https://doi.org/10.48550/arXiv.2309.05519
Nguyen, V.-Q., Suganuma, M., & Okatani, T. (2021). Look wide and interpret twice: Improving performance on interactive instruction-following tasks. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21) Main Track (pp. 923–930). https://doi.org/10.24963/ijcai.2021/128
Wang, H., Liang, W., Van Gool, L., & Wang, W. (2023). DREAMWALKER: Mental planning for continuous vision-language navigation. arXiv:2308.07498. https://doi.org/10.48550/arXiv.2308.07498
Zand, J., Parker-Holder, J., & Roberts, S. J. (2022). On-the-fly strategy adaptation for ad-hoc agent coordination. arXiv:2203.08015. https://doi.org/10.48550/arXiv.2203.08015
Li, Y., Zhang, S., Sun, J., Zhang, W., Du, Y., Wen, Y., Wang, X., & Pan, W. (2024). Tackling cooperative incompatibility for zero-shot human-AI coordination. Journal of Artificial Intelligence Research, 80, 1139–1185. https://doi.org/10.1613/jair.1.15884
Hong, J., Levine, S., & Dragan, A. (2023). Learning to influence human behavior with offline reinforcement learning. Advances in Neural Information Processing Systems (NeurIPS 2023), 36, 36094–36105. https://doi.org/10.52202/075280-1565
Peng, Z., Mo, W., Duan, C., Li, Q., & Zhou, B. (2023). Learning from active human involvement through proxy value propagation. Advances in Neural Information Processing Systems, 36, 77969–77992.
Xu, M., Niyato, D., Kang, J., Xiong, Z., Mao, S., Han, Z., Kim, D. I., & Letaief, K. B. (2024). When large language model agents meet 6G networks: Perception, grounding, and alignment. IEEE Wireless Communications, 31(6), 63–71. https://doi.org/10.1109/MWC.005.2400019
Hu, Y., Teng, Y., Zhang, Y., Li, Q., Zhang, Y., & Song, X. (2024). AI service deployment and resource allocation optimization based on human-like networking architecture. IEEE Internet of Things Journal, 11(14), 24795–24813. https://doi.org/10.1109/JIOT.2024.3384546
Alarcon, M. L., Kambhampati, A., Roy, U., Nguyen, P. P., Attari, M., Surya, R., Bunyak, F., Maschmann, M. R., Palaniappan, K., & Calyam, P. (2024). Learning-based image analytics in user-AI agent interactions for cyber-enabled manufacturing. 2024 IEEE 4th International Conference on Human-Machine Systems (ICHMS) (pp. 1–7). IEEE. https://doi.org/10.1109/ICHMS59971.2024.10555867
Strinati, E. C., Barbarossa, S., Choi, J., Madi, M. A., & Destounis, A. (2024). Goal-oriented and semantic communication in 6G AI-native networks: The 6G-GOALS approach. 2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) (pp. 1–6). IEEE. https://doi.org/10.1109/EuCNC/6GSummit60053.2024.10597087
Ayub, A., & Wagner, A. R. (2023). CBCL-PR: A cognitively inspired model for class-incremental learning in robotics. IEEE Transactions on Cognitive and Developmental Systems, 15(4), 2004–2013. https://doi.org/10.1109/TCDS.2023.3299755
Such, F. P., Rawal, A., Lehman, J., Stanley, K. O., & Clune, J. (2020). Generative teaching networks: Accelerating neural architecture search by learning to generate synthetic training data. Proceedings of the 37th International Conference on Machine Learning (pp. 9206–9216). PMLR.
Ye, D., Chen, G., Zhang, W., Yu, S., Yuan, X., Yuan, B., Liu, Z., Yang, L., Guo, J., Yu, Q., Bi, X., Wang, P., Qiu, M., Cheng, H., Yin, J., & Tang, J. (2020). Towards playing full MOBA games with deep reinforcement learning. Advances in Neural Information Processing Systems, 33, 621–632.
Ye, D., Liu, Z., Sun, M., Shi, B., Zhao, P., Wu, H., … Huang, L. (2020). Mastering complex control in MOBA games with deep reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6672–6679. https://doi.org/10.1609/aaai.v34i04.6144
Zha, D., Xie, J., Ma, W., Zhang, S., Lian, X., Hu, X., & Liu, J. (2021). DouZero: Mastering DouDizhu with self-play deep reinforcement learning. Proceedings of the 38th International Conference on Machine Learning (pp. 12333–12344). PMLR.
Lan, Y. J., & Chen, N. S. (2024). Teachers’ agency in the era of LLM and generative AI: Designing pedagogical AI agents. Educational Technology & Society, 27(1), 1–18. https://doi.org/10.30191/ETS.202401_27(1).PP01
Abhinav, K., Subramanian, V., Dubey, A., Bhat, P., & Venkat, A. D. (2018). LeCoRe: A framework for modeling learner’s preference. Proceedings of the 11th International Conference on Educational Data Mining (EDM 2018). Buffalo, NY, USA. http://educationaldatamining.org/files/conferences/EDM2018/papers/EDM2018_paper_69.pdf
de Lima, E. S., Neggers, M. M. E., Feijo, B., Casanova, M. A., & Furtado, A. L. (2025). An AI-powered approach to the semiotic reconstruction of narratives. Entertainment Computing, 52, 100810. https://doi.org/10.1016/j.entcom.2024.100810
Bhunia, A.K., Das, A., Muhammad, U.R., Yang, Y., Hospedales, T.M., Xiang, T., Gryaditskaya, Y., & Song, Y. (2020). Pixelor. ACM Transactions on Graphics (TOG), 39, 1–15.
Sinha, M., Healey, J., & Sengupta, T. (2020). Designing with AI for digital marketing. Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’20) (pp. 65–70). Association for Computing Machinery. https://doi.org/10.1145/3386392.3397600
Tara, A., Taban, N., & Turesson, H. (2022). Performance analysis of an ontology model enabling interoperability of artificial intelligence agents. Artificial Intelligence Trends in Systems (pp. 395–406). Springer International Publishing. https://doi.org/10.1007/978-3-031-09076-9_35
Kalech, M., & Stern, R. (2020). AI for software quality assurance blue sky ideas talk. Proceedings of the AAAI Conference on Artificial Intelligence, 34(9), 13529–13533. https://doi.org/10.1609/aaai.v34i09.7076
Senthil Velan, S. (2019). Introducing artificial intelligence agents to the empirical measurement of design properties for aspect oriented software development. 2019 Amity International Conference on Artificial Intelligence (AICAI) (pp. 80–85). https://doi.org/10.1109/AICAI.2019.8701250
Xu, J., & Howard, A. M. (2020). How much do you trust your self-driving car? Exploring human-robot trust in high-risk scenarios. 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 4273–4280). https://doi.org/10.1109/SMC42975.2020.9282866
Fuchs, A., Passarella, A., & Conti, M. (2022). A cognitive framework for delegation between error-prone AI and human agents. 2022 IEEE International Conference on Smart Computing (SMARTCOMP) (pp. 317–322). https://doi.org/10.1109/SMARTCOMP55677.2022.00074
Skulmowski, A. (2024). Placebo or assistant? Generative AI between externalization and anthropomorphization. Educational Psychology Review, 36(2), 58. https://doi.org/10.1007/s10648-024-09894-x
Vetrò, A., Santangelo, A., Beretta, E., & De Martin, J. C. (2019). AI: From rational agents to socially responsible agents. Digital Policy, Regulation and Governance, 21(3), 291–304. https://doi.org/10.1108/DPRG-08-2018-0049
Shilov, N. G., Ponomarev, A. V., & Smirnov, A. V. (2023). The analysis of ontology-based neuro-symbolic intelligence methods for collaborative decision support. Informatics and Automation, 22(3), 576–615.
Kulkarni, A., Sreedharan, S., Keren, S., Chakraborti, T., Zha, Y., & Kambhampati, S. (2019). Explicable planning as minimizing distance from expected behavior. Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS’19) (pp. 774–782). International Foundation for Autonomous Agents and Multiagent Systems.
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., ... & Gu, J. (2023). The rise and potential of large language model based agents: A survey. arXiv:2309.07864. https://doi.org/10.48550/arXiv.2309.07864
Li, X., Li, Y., Zhang, J., Xu, H., Chen, M., & Huang, X. (2024). A review of prominent paradigms for LLM-based agents: Tool use, planning (including RAG), and feedback learning. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) (pp. 9760–9779).
Händler, T. (2023). Balancing autonomy and alignment: A multi-dimensional taxonomy for autonomous LLM-powered multi-agent architectures. arXiv.2310.03659. https://doi.org/10.48550/arXiv.2310.03659
Li, X., Wang, Y., Zhang, L., Liu, T., & Sun, M. (2024). A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges. Vicinagearth, 1, 9. https://doi.org/10.1007/s44336-024-00009-2
Masterman, T., Besen, S., Sawtell, M., & Chao, A. (2024). The landscape of emerging AI agent architectures for reasoning, planning, and tool calling: A survey. arXiv:2404.11584. https://doi.org/10.48550/arXiv.2404.11584
Kasirzadeh, A., & Gabriel, I. (2025). Characterizing AI agents for alignment and governance. arXiv:2504.21848. https://doi.org/10.48550/arXiv.2504.21848
Zhou, J., Li, C., Chen, S., Wu, Y., & Xu, D. (2024). A taxonomy of architecture options for foundation model-based agents: Analysis and decision model. arXiv:2408.02920. https://doi.org/10.48550/arXiv.2408.02920
Kelly, S., Kaye, S.-A., & Oviedo-Trespalacios, O. (2023). What factors contribute to the acceptance of artificial intelligence? A systematic review. Telematics and Informatics, 77, 101925. https://doi.org/10.1016/j.tele.2022.101925
Jiangshu, Y., Zhang, S., Liang, H., Zhang, H., & Li, Y. (2025). AI agents: A development guide. Moscow: DMK Press. (In Russian).
Borne, P., Anderson, K., Woods, M., & Dimitrova, N. (2025). Agentic artificial intelligence: A guide to business transformation. Moscow: DMK Press. (In Russian).
Glukhov, A. P. (2025). AI agents in tutoring: Potential, challenges, and prospects for integration. Journal of Pedagogical Innovations, 1(77), 65–74 (in Russian). https://doi.org/10.15293/1812-9463.2501.06
Berman, N. D. (2025). Digital marketing: Using artificial intelligence for competitive strategies. CITISE, 2(44), 40–48 (in Russian).
Guzenko, O. I., & Balyabin, D. S. (2025). AI agents in project management: Opportunities, limitations, and integration strategies. Project Management Bulletin, 1(2), 71–78 (in Russian).
Ignatyev, V. I. (2019). And a “different” actor is coming… The formation of a techno-subject in the context of the movement towards technological singularity. Sociology of Science and Technology, 10(1), 64–78 (in Russian). https://doi.org/10.24411/2079-0910-2019-10005
Copyright (c) 2026 National Research University Higher School of Economics
This work is licensed under a Creative Commons Attribution 4.0 International License.
