#Agent4DL#Generative Agents#Digital Libraries#User Simulation#Privacy-Preserving Research#Large Language Models#Information Retrieval#Search Behavior Modeling
📌 Key Takeaways
Agent4DL simulates realistic user search behaviors in digital libraries
The tool addresses privacy concerns by generating synthetic user interaction data
Researchers validated the simulator against real user data
Agent4DL outperforms existing simulators in generating diverse, context-aware behaviors
The research enables privacy-compliant study of digital library user behavior
📖 Full Retelling
Computer science researchers Saber Zerhoudi and Michael Granitzer introduced Agent4DL, a user search behavior simulator for digital libraries, in their paper submitted to arXiv on February 26, 2026, addressing the longstanding challenge of scarce publicly available user search data due to privacy concerns. The paper titled 'Generative Agents Navigating Digital Libraries' presents Agent4DL as a sophisticated tool designed to generate realistic user profiles and dynamic search sessions that mimic actual search behaviors including querying, clicking, and stopping patterns tailored to specific user types. The researchers validated their simulator's accuracy by comparing its outputs with real user interaction data, demonstrating that Agent4DL can replicate authentic user behaviors with high fidelity. Notably, the tool shows competitive performance against existing user search simulators like SimIIR 2.0, with particular strength in generating more diverse and context-aware user behaviors that better reflect the complexity of real digital library interactions. The research falls at the intersection of Information Retrieval, Artificial Intelligence, and Digital Libraries, highlighting how large language models can be leveraged to overcome data scarcity challenges in digital library research.
🏷️ Themes
Digital Libraries, Artificial Intelligence, Information Retrieval, User Behavior Simulation
Information retrieval (IR) in computing and information science is the task of identifying and retrieving information system resources that are relevant to an information need. The information need can be specified in the form of a search query. In the case of document retrieval, queries can be base...
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pre-trained transformers (GPTs) that provide the c...
--> Computer Science > Information Retrieval arXiv:2602.22529 [Submitted on 26 Feb 2026] Title: Generative Agents Navigating Digital Libraries Authors: Saber Zerhoudi , Michael Granitzer View a PDF of the paper titled Generative Agents Navigating Digital Libraries, by Saber Zerhoudi and 1 other authors View PDF HTML Abstract: In the rapidly evolving field of digital libraries, the development of large language models has opened up new possibilities for simulating user behavior. This innovation addresses the longstanding challenge in digital library research: the scarcity of publicly available datasets on user search patterns due to privacy concerns. In this context, we introduce Agent4DL, a user search behavior simulator specifically designed for digital library environments. Agent4DL generates realistic user profiles and dynamic search sessions that closely mimic actual search strategies, including querying, clicking, and stopping behaviors tailored to specific user profiles. Our simulator's accuracy in replicating real user interactions has been validated through comparisons with real user data. Notably, Agent4DL demonstrates competitive performance compared to existing user search simulators such as SimIIR 2.0, particularly in its ability to generate more diverse and context-aware user behaviors. Subjects: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Digital Libraries (cs.DL) Cite as: arXiv:2602.22529 [cs.IR] (or arXiv:2602.22529v1 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2602.22529 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Journal reference: Proceedings of the 26th International Conference on Asia-Pacific Digital Libraries, ICADL 2024 Related DOI : https://doi.org/10.1007/978-981-96-0865-2_14 Focus to learn more DOI linking to related resources Submission history From: Saber Zerhoudi [ view email ] [v1] Thu, 26 Feb 2026 02:08:39 UTC (58 KB) Full-text links: Access Paper: View a PDF of the paper t...
