Focus Group-Led Refinement of an LLM-Enabled Companion Robot for Older People

Abstract Loneliness in later life is a public‑health concern, and large language model (LLM)-enabled conversational robots have potential to supplement social connection at scale by facilitating everyday conversations. However, evidence on the development and acceptability of such systems for older people remains scarce. We conducted a two‑round mixed methods study with older community‑dwelling participants, to test whether pipeline refinements—streaming automatic speech recognition, text‑to‑speech, and simplified turn‑taking cues—improved conversational experience. A tabletop conversational robot (Sota, Vstone), powered by Generative Pre‑trained Transformer (GPT)‑4o was used. Eighteen individuals participated in round one; paired analyses were conducted on the 17 eligible participants remaining in round two. We collected interaction logs (response latency, LLM‑level latency, and deletion rate proportion of words in the manual transcript omitted in the ASR output), technical failure events, and participant questionnaires (Godspeed Questionnaire Series; System Usability Scale; a customised five-item scale assessing conversational experience). Qualitative data were analysed using a framework approach. Median response latency decreased from 9.8 to 4.7s, deletion rate from 0.37 to 0.07, accompanied by improved perceived usability and conversational naturalness, while questionnaire indices of companionship changed little. Qualitative accounts converged: interactions felt smoother and more in‑context, yet interruptions, perceived superficiality of conversation, and only a modest sense of companionship were still experienced. Findings indicate that improving basic conversational fluency enhances naturalness and usability but is insufficient for delivering truly relational experience outcomes. Progress toward better companionship requires an additional relational layer—shared memories, age‑attuned personas, and calibrated reciprocity.