The identity design of artificial agents carries growing ethical, psychological, and cultural weight, as ubiquitous language models and diverse robotic forms are blended into everyday use. However, structured approaches to designing coherent and interpretable artificial identities remain limited. To address urgent challenges in artificial identity design, including harmful stereotypes and deceptive practices, we introduce the Identity Design (ID) Framework and an accompanying research agenda. Drawing on emerging work on artificial identity in human-robot interaction and taking an interdisciplinary perspective, we propose twelve design principles across three levels: individual (recognisability, behavioural consistency, identity continuity, memory, persistent goals), group (membership signalling, social alignment, role clarity), and societal (benevolence, artificiality, social justice, transparency). The research agenda outlines open questions around the operationalisation and measurement of identity, social dynamics, and ethical considerations for identity design. Together, they lay the groundwork for future research and responsible practice in robotic, virtual, and multi-embodied agents.

Although embodied AI systems are increasingly developed and tested in public environments, their influence on the design of products for older adults remains underexplored. We examine how different types of embodiment, or form factor, shape initial encounters between humans and AI when conversational abilities are comparable. Building on prior work, we conducted a two-day field study at a senior citizens’ fair in Germany (n = 25, age 24–90), where participants interacted with the screen-based avatar Ann-Sophie and the humanoid robot Ameca. Both used LLM-based dialogue systems, enabling a focus on embodied interaction rather than linguistic performance. Qualitative results show contrasting affective and social responses: Ameca’s physical presence and gaze dynamics were described as both fascinating and unsettling, while Ann-Sophie was perceived as warm but socially limited. These findings highlight the role of embodiment in shaping comfort, expectations, and ethical awareness in public human–AI interaction.

Large language models (LLMs), when integrated into social robots, have the potential to transform robot-assisted language learning by offering personalized, interactive communication. However, there is limited research exploring their potential to simultaneously reduce anxiety and enhance language-speaking skills among international university students, who often feel anxious when speaking a foreign language. This study addresses this gap by evaluating the impact of a humanoid robot powered by the OpenChat-3.5 LLM as a tandem partner for German language learning. Using a between-subjects design with 22 multilingual participants, two interaction conditions were tested: immersive (German-only) and bilingual (German-English). Our findings indicate that participants in the immersive mode reported experiencing significantly reduced perceived judgment by the robot compared to the bilingual mode. Although female participants showed a trend of greater improvement in learning gain, no significant gender differences were found. Open-ended feedback highlighted the need for enhanced contextual responses, slower speech rate, faster response times, and error corrections to enhance language speaking support. This study aims to advance social robots for learning by demonstrating the usage of generative AI in creating non-judgmental language practice scenarios.

Backstory enriches the depth of a character by providing context and history. This online study explored how social robots narrating emotional backstories affect human empathy. Three backstories-happy, neutral (control), and sad- were crafted to mirror believable robot experiences. These narratives, personified as the robot's emotions, were conveyed through multi-modal video recordings of the robot that featured visual and textual elements. A within-subject experiment was conducted through a web-based survey among 60 English-speaking students from a German university. Our results highlight the significant role of backstories in shaping perceptions of robots, with the sad backstory notably increasing empathy towards social robots, diverging from prior Human-Robot Interaction paradigms. Furthermore, gender-based differences in empathetic responses highlighted the impact of sad narratives on female participants, with the robot's voice set as female. Open-ended feedback suggested the need for improved expressiveness in facial expressions and gaze strategies to mitigate the uncanny valley phenomenon.

Highly anthropomorphic robots risk triggering expectation mismatch that can lead to disappointment when robot behavior falls short. This study investigates how actively teaching a social humanoid robot to narrate a story influences user expectations, negative attitudes, anxiety, and perceptions of storytelling quality, compared to passive observation. University students (N=40) were assigned to either a teaching or non-teaching condition. Teaching participants instructed the robot using speech and gestures, while the non-teaching group observed the robot narrate the resulting storytelling video. Results showed that active teaching reduced expectation shifts, suggesting greater alignment between user beliefs and robot capability. However, robot-related anxiety increased in the teaching group, while the non-teaching group consistently reported higher negative attitudes. Storytelling quality was more strongly influenced by robot anthropomorphism in the non-teaching group. Participants who blamed the robot gave lower storytelling ratings, whereas those who blamed the AI model or programmer were more lenient. These findings highlight the importance of managing expectations through interactive teaching of robot tutee.

The presented study investigated the dressing style preference of human interlocutors for the social robot, ROBIN, in a university setting. Through an online questionnaire format, the research examined the impact of robot attire on human-robot interaction (HRI), and the perception of social robots in a social context. A mixed-methods approach was employed, conducting within-subjects empirical study via an online questionnaire that consisted of user demographics, social factors, constructs of robot usage, and two identical HRI videos. The videos featured ROBIN, a humanoid robot, dressed in formal vs. casual attire, respectively, as a representative from the student service center interacting with a human student. The findings indicated that 51.35% probable human interlocutors expressed a preference for the casual clothing style, while 48.65% preferred formal style. Additionally, participants associated social traits such as friendly, helpful, comfortable, approachable, and interesting with the robot’s casual attire. This study highlights the significance of robot clothing in personalized HRI, and its impact on perception of social robots by humans. Analyzing the interlocutor preferences for robot dressing style, it emphasizes clothing as an influential factor in the design of socially acceptable robots.