Generative Agents Navigating Digital Libraries

2026-02-25

AI Summary

This work addresses the scarcity of authentic user search behavior data in digital library research, a limitation often imposed by privacy constraints. To overcome this challenge, the authors propose Agent4DL—the first generative agent framework specifically designed for digital libraries. By integrating large language models with user profiles, Agent4DL dynamically simulates context-aware, personalized search sessions that include queries, clicks, and stopping behaviors. Compared to existing tools such as SimIIR 2.0, Agent4DL demonstrates significantly enhanced behavioral diversity and contextual adaptability, effectively replicating real-world user interaction patterns. The framework thus establishes a high-fidelity, scalable simulation paradigm for information retrieval research, offering a robust alternative to empirical user studies while preserving ecological validity.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

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.

Problem

• digital libraries
• user search behavior
• data scarcity
• privacy concerns
• search patterns

Innovation

• Generative Agents
• Digital Libraries
• User Search Simulation
• Large Language Models
• Behavior Modeling