Generative Agents Navigating Digital Libraries
This work provides a solution for digital library researchers to overcome data scarcity for user search patterns, which is crucial for improving digital library design and functionality.
This paper introduces Agent4DL, a user search behavior simulator for digital libraries, addressing the lack of public user search pattern datasets. It generates realistic user profiles and dynamic search sessions, validated against real user data, and shows competitive performance against existing simulators like SimIIR 2.0, with more diverse and context-aware behaviors.
In the rapidly evolving field of digital libraries, the development of large language models (LLMs) 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.