Designing Adaptive LLM-Based Social Robots for Retail Sales Consultations

Advancements in social robotics and large language models (LLMs) offer new opportunities to enhance consumer experiences in retail settings. This study investigates how an adaptive LLM-based social robot should be designed to facilitate consumers’ purchase decision-making during sales consultations. Employing a design science research approach and drawing on Social Response Theory and Media Naturalness Theory, we identified key issues and requirements and, on this basis, derived three design principles focusing on the robot’s verbal and non-verbal communication style. We instantiate the design principles in a running social robot building on the commercial Furhat robotics platform and OpenAI LLMs with two design variants: rational and emotional. Participants interacted with the social robot in a laboratory experiment while receiving product advice. The results indicate that the rational design variant significantly increased purchase intentions. Our research contributes to the design of adaptive LLM-based social robots in retail by demonstrating that rational verbal communication and rational non-verbal communication positively influence consumers’ purchase intentions.