Balancing automation and control: user perceptions of tool invocations in conversational agents. Hennekeuser, D., Vaziri, D. D., Golchinfar, D., Schreiber, D., & Stevens, G. i-com, Oldenbourg Wissenschaftsverlag, 2026.
Balancing automation and control: user perceptions of tool invocations in conversational agents [link]Paper  doi  abstract   bibtex   
Advances in large language models (LLMs) have enabled conversational agents (CAs) to invoke external functions dynamically, yet little is known about how different tool-calling (TC) strategies affect user experience. This study compares two approaches – automatic execution based on conversational context versus user-confirmed execution – using a German-language CA in a business-travel scenario. In a between-subjects experiment, 451 employed adult participants (aged 18–65) were randomly assigned to one of the two TC conditions, completed a structured travel request interaction, and then rated their perceived trust (PTru), autonomy (PA), transparency (PTrn), ease of use (PEU), and usefulness (PU). Our findings indicate that TC strategy had a significant overall impact on users’ combined perceptions, and that demographic factors – particularly age – played a critical role in shaping these responses, highlighting the need for adaptive, inclusive design practices that balance automation with user control. CCS Concepts • Human-centered computing → Human computer interaction (HCI) → Interactive systems and tools • Human-centered computing → Interaction design → Systems and tools for interaction design.
@article{hennekeuserBalancingAutomationControl,
	title = {Balancing automation and control: user perceptions of tool invocations in conversational agents},
	copyright = {De Gruyter expressly reserves the right to use all content for commercial text and data mining within the meaning of Section 44b of the German Copyright Act.},
	issn = {2196-6826},
	shorttitle = {Balancing automation and control},
	url = {https://www.degruyterbrill.com/document/doi/10.1515/icom-2025-0053/html},
	doi = {10.1515/icom-2025-0053},
	abstract = {Advances in large language models (LLMs) have enabled conversational agents (CAs) to invoke external functions dynamically, yet little is known about how different tool-calling (TC) strategies affect user experience. This study compares two approaches – automatic execution based on conversational context versus user-confirmed execution – using a German-language CA in a business-travel scenario. In a between-subjects experiment, 451 employed adult participants (aged 18–65) were randomly assigned to one of the two TC conditions, completed a structured travel request interaction, and then rated their perceived trust (PTru), autonomy (PA), transparency (PTrn), ease of use (PEU), and usefulness (PU). Our findings indicate that TC strategy had a significant overall impact on users’ combined perceptions, and that demographic factors – particularly age – played a critical role in shaping these responses, highlighting the need for adaptive, inclusive design practices that balance automation with user control. CCS Concepts • Human-centered computing → Human computer interaction (HCI) → Interactive systems and tools • Human-centered computing → Interaction design → Systems and tools for interaction design.},
	language = {en},
	urldate = {2026-03-02},
	journal = {i-com},
	publisher = {Oldenbourg Wissenschaftsverlag},
	author = {Hennekeuser, Darius and Vaziri, Daryoush Daniel and Golchinfar, David and Schreiber, Dirk and Stevens, Gunnar},
	year = {2026},
	keywords = {conversational agent, function calling, large language models, tool calling},
}

Downloads: 0