Institution profile

University of Passau

Academic institutioneurope · de
Official website
Research library94linked papers
Opportunities0open roles
Selected work

Representative Papers

UXSim: Towards a Hybrid User Search Simulation

Nov 10, 2025International Conference on Information and Knowledge Management

Existing approaches struggle to accurately capture the dynamic and personalized nature of user behavior in interactive search, as static agents or purely large language model (LLM)-based agents often lack grounding in real-world data. This work proposes UXSim, a novel framework that uniquely integrates traditional data-driven user simulators with adaptive LLM agents. By leveraging real user interaction logs to constrain and guide the LLM’s reasoning process, UXSim ensures behavioral fidelity while enhancing the interpretability of the underlying cognitive mechanisms. The resulting simulation not only achieves greater accuracy and dynamism in modeling user search behaviors but also enables verifiable explanations of simulated outcomes, thereby bridging the gap between data realism and generative flexibility in user modeling.

2 citationsRead paper

Sojourner under Sabotage: A Serious Testing and Debugging Game

Apr 27, 2025

Software testing and debugging instruction often suffers from low student engagement and perceived task monotony. To address this, we designed and implemented a browser-based serious game centered on troubleshooting malfunctions in a fictional spacecraft, structured into seven progressive levels that systematically develop unit test writing and debugging competencies. Our approach innovatively incorporates a sabotage mechanism—intentional introduction of faults—to cultivate proactive problem detection. The system integrates educational data tracking with quantifiable behavioral analytics to enable closed-loop, formative assessment. Developed using HTML5 and JavaScript, the platform ensures accessibility and pedagogical adaptability. A controlled study with 79 students demonstrated statistically significant improvements: learning motivation increased significantly (p < 0.01), debugging task completion rose by 37%, and adherence to unit test best practices improved by 42%.

1 citationsRead paper
Recent publications

Latest Papers