# "MeBo Leaves a Piece of You Behind": Designing a Relational Voice-Based Memory Companion for Older Adults

arXiv: https://arxiv.org/abs/2609.24706 · HTML: https://mlsanity.com/paper/2609.24706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 138 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation](https://mlsanity.com/paper/2403.02135/) (2024)
- [Understanding the Impact of Long-Term Memory on Self-Disclosure with Large Language Model-Driven Chatbots for Public Health Intervention](https://mlsanity.com/paper/2402.11353/) (2024)
- [Comparing How a Chatbot References User Utterances from Previous Chatting Sessions: An Investigation of Users' Privacy Concerns and Perceptions](https://mlsanity.com/paper/2308.04879/) (2023)
- [Like My Aunt Dorothy: Effects of Conversational Styles on Perceptions, Acceptance and Metaphorical Descriptions of Voice Assistants during Later Adulthood](https://mlsanity.com/paper/2309.11681/) (2023)
- [Understanding Barriers and Design Opportunities to Improve Healthcare and QOL for Older Adults through Voice Assistants](https://mlsanity.com/paper/2111.03756/) (2021)
- [Polite or Direct? Conversation Design of a Smart Display for Older Adults Based on Politeness Theory](https://mlsanity.com/paper/2203.15767/) (2022)
- [Exploring the Design of Generative AI in Supporting Music-based Reminiscence for Older Adults](https://mlsanity.com/paper/2403.01413/) (2024)
- ["Death" of a Chatbot: Investigating and Designing Toward Psychologically Safe Endings for Human-AI Relationships](https://mlsanity.com/paper/2602.07193/) (2026)
- [Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment](https://mlsanity.com/paper/2602.23436/) (2026)
- [Situated Participatory Design: A Method for In Situ Design of Robotic Interaction with Older Adults](https://mlsanity.com/paper/2302.00588/) (2023)
- [Exploring the Opportunities of AR for Enriching Storytelling with Family Photos between Grandparents and Grandchildren](https://mlsanity.com/paper/2309.03533/) (2023)
- [Understanding and Co-designing Photo-based Reminiscence with Older Adults](https://mlsanity.com/paper/2411.00351/) (2024)
- [Memory Reviver: Supporting Photo-Collection Reminiscence for People with Visual Impairment via a Proactive Chatbot](https://mlsanity.com/paper/2501.15408/) (2025)
- [Remini: Leveraging Chatbot-Mediated Mutual Reminiscence for Promoting Positive Affect and Feeling of Connectedness among Loved Ones](https://mlsanity.com/paper/2508.03355/) (2025)
- [Sometimes You Need Facts, and Sometimes a Hug: Understanding Older Adults' Preferences for Explanations in LLM-Based Conversational AI Systems](https://mlsanity.com/paper/2510.06697/) (2025)
- [Investigating the Potential of Artificial Intelligence Powered Interfaces to Support Different Types of Memory for People with Dementia](https://mlsanity.com/paper/2211.10756/) (2022)
- [Beyond Functionality: Co-Designing Voice User Interfaces for Older Adults' Well-being](https://mlsanity.com/paper/2409.08449/) (2024)
- ["Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations](https://mlsanity.com/paper/2603.09012/) (2026)
- [Designing with Tensions: Older Adults' Emotional Support-Seeking Under System-Level Constraints in Conversational AI](https://mlsanity.com/paper/2605.05552/) (2026)

## Abstract (arXiv)

Autobiographical remembering supports identity, well-being, and social connection in later life, yet voice-based memory technologies largely rely on isolated prompts. We designed and built MeBo, a fully functional relational voice-based memory companion, through participatory design with 11 older adults. Their accounts shaped four Design Strategies that guided MeBo's interaction design and multi-agent implementation. In a mixed-methods evaluation with 20 older adults, participants found MeBo exceptionally usable (SUS = 87.75), enjoyable, sociable, emotionally responsive, and trustworthy. Participants reported higher positive affect and momentary social connection and lower negative affect after the session than before. Participants described how MeBo followed their stories, returned to earlier memories, adapted to their preferences, and made its growing memory visible and controllable. MeBo's relational framing surfaces tensions around what it should remember, who may access memories produced through interaction, and what becomes of them when the user or MeBo is no longer present.