LLM-based embodied agents are recently emerging in VR, supporting various scenarios such as pedagogical assistants, virtual companions, and NPCs for games. These agents hold potential to enhance user interactions but require thoughtful design to cater diverse user needs and contexts. We present an architecture that leverages different LLM modules to enable conversational interactions with an embodied agent in multi-user VR. Our system’s primary goal is to facilitate immersive tailoring through conversational input, allowing users to dynamically adjust an agent’s behavior and properties (e.g., role, personality, and appearance), directly within the virtual space, rather than during development or via separate interfaces. We evaluate the system’s performance, measuring latency during tailoring tasks, and share insights from a six-week study involving five users exploring various scenarios. While the approach shows promise, challenges remain, including reducing latency in the speech-to-text-to-speech pipeline and addressing the black-box limitations of LLMs, highlighting areas for future research.

Abstract Differences in cognitive abilities affect search behaviors, but this has mostly been observed in laboratory experiments. There is limited research on how users search for information in real‐world, naturalistic settings and how real‐world search behaviors relate to cognitive abilities. In this study, we investigated a wide range of behavioral data captured from real‐life search tasks, their association with users' cognitive abilities, and the potential for automatically inferring cognitive abilities from these data. Furthermore, we aimed to determine the data quantity and monitoring duration needed to effectively estimate cognitive abilities from naturalistic behavior. Twenty individuals with βvarying cognitive abilities participated in the experiments in which their everyday search behavior was continuously recorded for 14 days. Their cognitive ability was evaluated through standard tests conducted individually. Data consisted of over 800 h of monitoring, including 2022 queries extracted from 1,442,447 screen frames and associated operating system logs. Using these data, naturalistic search behaviors were associated with cognitive abilities, and predictive models were trained. The results showed that lower selective attention was found to be associated with longer dwelling on selected search results. Faster psychomotor speed and higher fluid intelligence were found to be associated with a greater amount of text read on selected pages. Predictive models exhibited small error rates in predicting cognitive abilities.

Web search ranking models learn from human interactions to improve retrieval performance, but they are presently limited by their use of behavioral factors, such as click-through data or dwell time, that do not account for differences in their users’ cognition. However, it is well understood that users’ behavior varies according to their abilities in processing information, making inferences, and interacting with computing systems. As a result, researchers may miss opportunities to design ranking models that are optimized for their users’ cognitive abilities. To address this, we report an approach for search result re-ranking that incorporates cognitive ability information in the ranking model. We report extensive empirical in-the-wild experiments with data from simulated tasks and real-world tasks of 20 participants to measure, predict, and use these data to train search result re-ranking models. Our results demonstrate that cognitive ability data significantly improve the effectiveness of re-ranking models in simulated-task and real-world conditions, and that cognitive abilities can be predicted from regular user interactions without requiring separate cognitive testing for each user. In particular, the models show improved performance in predicting the position of the documents the users select during search sessions. Our findings show that search engines have significant potential to improve their ranking performance by accounting for users’ cognitive ability.