English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Designing and evaluating personalized and proactive assistant agents remainschallenging due to the time, cost, and ethical concerns associated withhuman-in-the-loop experimentation. Existing Human-Computer Interaction (HCI)methods often require extensive physical setup and human participation, whichintroduces privacy concerns and limits scalability. Simulated environmentsoffer a partial solution but are typically constrained by rule-based scenariosand still depend heavily on human input to guide interactions and interpretresults. Recent advances in large language models (LLMs) have introduced thepossibility of generative agents that can simulate realistic human behavior,reasoning, and social dynamics. However, their effectiveness in modelinghuman-assistant interactions remains largely unexplored. To address this gap,we present a generative agent-based simulation platform designed to simulatehuman-assistant interactions. We identify ten prior studies on assistant agentsthat span different aspects of interaction design and replicate these studiesusing our simulation platform. Our results show that fully simulatedexperiments using generative agents can approximate key aspects ofhuman-assistant interactions. Based on these simulations, we are able toreplicate the core conclusions of the original studies. Our work provides ascalable and cost-effective approach for studying assistant agent designwithout requiring live human subjects. We will open source both the platformand collected results from the experiments on our website:https://dash-gidea.github.io/.

Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies