Agentic Search Systems with Persistent Memory for Complex Web Information Retrieval
Keywords:
agentic search, persistent memory, retrieval-augmented generation, web agents, governance, information retrieval, system architectureAbstract
The growing complexity of web information retrieval has exposed the limitations of stateless retrieval-augmented generation systems, which typically process each query independently and lack durable representations of user intent, source reliability, and task context. Agentic search systems address this gap by combining large language models with persistent memory, tool use, and multi-step control loops. This article provides a system-level analysis of such architectures, focusing on structural trade-offs rather than isolated model accuracy. It examines how persistent memory can support query matching, intent modeling, source selection, and long-horizon task execution while introducing new risks related to stale information, privacy, bias, and source monoculture. The discussion integrates perspectives from retrieval infrastructure, planning, web interaction, evaluation, governance, and sustainability. The article argues that persistent memory should be treated as a governed, revisable layer rather than an unrestricted accumulation of user traces. Deployment considerations include the separation of long-term user profiles from ephemeral session state, the alignment of retrieval infrastructure with organizational policy, and the environmental cost of repeated inference and memory maintenance. The analysis highlights the need for auditable memory architectures, adaptive retrieval policies, and evaluation frameworks that account for fairness, robustness, and socio-technical impact. By connecting foundational research on memory networks and retrieval-augmented generation with recent advances in web agents and tool orchestration, the article offers a forward-looking account of how agentic search systems can be designed responsibly for complex web information retrieval.
References
1. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
2. Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623.
3. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., ... Liang, P. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258.
4. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
5. Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769–6781.
6. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M.-W. (2020). REALM: Retrieval-augmented language model pre-training. Proceedings of the 37th International Conference on Machine Learning, 3929–3938.
7. Izacard, G., Lewis, P., Piktus, A., Petroni, F., Grave, E., Riedel, S., & Kiela, D. (2022). Atlas: Few-shot learning with retrieval augmented language models. arXiv preprint arXiv:2208.03299.
8. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations.
9. Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36, 68539–68551.
10. Yu, X. (2026). Enhancing Search Efficiency through LLM-Based User Memory Systems for Query Matching and Intent Modeling.
11. 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. Advances in Neural Information Processing Systems, 35, 24824–24837.
12. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., & Yao, S. (2023). Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36, 8634–8652.
13. 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 the 36th Annual ACM Symposium on User Interface Software and Technology, 1–22.
14. Sumers, T. R., Yao, S., Narasimhan, K., & Griffiths, T. L. (2023). Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427.
15. Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Dwivedi-Yu, J., Celikyilmaz, A., Grave, E., LeCun, Y., & Scialom, T. (2023). Augmented language models: A survey. arXiv preprint arXiv:2302.07842.
16. Weston, J., Chopra, S., & Bordes, A. (2015). Memory networks. International Conference on Learning Representations.
17. Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., Colmenarejo, S. G., Grefenstette, E., Ramalho, T., Agapiou, J., Badia, A. P., Hermann, K. M., Zwols, Y., Ostrovski, G., Cain, A., King, H., Summerfield, C., Blunsom, P., Kavukcuoglu, K., & Hassabis, D. (2016). Hybrid computing using a neural network with dynamic external memory. Nature, 538(7626), 471–476.
18. Lample, G., Sablayrolles, A., Ranzato, M., Denoyer, L., & Jégou, H. (2019). Large memory layers with product keys. Advances in Neural Information Processing Systems, 32, 8546–8557.
19. Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., Jiang, X., Cobbe, K., Eloundou, T., Krueger, G., Button, K., Knight, M., Chess, B., & Schulman, J. (2021). WebGPT: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332.
20. Deng, X., Gu, Y., Zheng, B., Chen, S., Stevens, S., Wang, B., Sun, H., & Su, Y. (2023). Mind2Web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems, 36, 28091–28114.
21. Zhou, S., Xu, F. F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Bisk, Y., Fried, D., Alon, U., & Neubig, G. (2024). WebArena: A realistic web environment for building autonomous agents. International Conference on Learning Representations.
22. Gur, I., Rueckert, U., Faust, A., & Hakkani-Tür, D. (2023). A real-world WebAgent with planning, long-term understanding, and programmatic synthesis. arXiv preprint arXiv:2307.12856.
23. Xiong, L., Xiong, C., Li, Y., Tang, K.-F., Liu, J., Bennett, P., Ahmed, J., & Overwijk, A. (2021). Approximate nearest neighbor negative contrastive learning for dense text retrieval. International Conference on Learning Representations.
24. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744.
25. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., ... Scialom, T. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Artificial Intelligence and Machine Learning Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.