Plural Voices, Single Agent: Towards Inclusive AI in Multi-User Domestic Spaces
This work addresses ethical and inclusion challenges in domestic AI for overlooked groups, representing a novel method for a known bottleneck rather than a foundational shift.
The paper tackles the problem of making domestic AI agents more inclusive for diverse users like children, elderly, and Neurodivergent individuals by introducing the Plural Voices Model (PVM), a single-agent framework that dynamically negotiates multi-user needs, resulting in improved compliance (76% vs. 70%), fairness (90% vs. 85%), and safety (0% vs. 7% violation rate) compared to baselines.
Domestic AI agents faces ethical, autonomy, and inclusion challenges, particularly for overlooked groups like children, elderly, and Neurodivergent users. We present the Plural Voices Model (PVM), a novel single-agent framework that dynamically negotiates multi-user needs through real-time value alignment, leveraging diverse public datasets on mental health, eldercare, education, and moral reasoning. Using human+synthetic curriculum design with fairness-aware scenarios and ethical enhancements, PVM identifies core values, conflicts, and accessibility requirements to inform inclusive principles. Our privacy-focused prototype features adaptive safety scaffolds, tailored interactions (e.g., step-by-step guidance for Neurodivergent users, simple wording for children), and equitable conflict resolution. In preliminary evaluations, PVM outperforms multi-agent baselines in compliance (76% vs. 70%), fairness (90% vs. 85%), safety-violation rate (0% vs. 7%), and latency. Design innovations, including video guidance, autonomy sliders, family hubs, and adaptive safety dashboards, demonstrate new directions for ethical and inclusive domestic AI, for building user-centered agentic systems in plural domestic contexts. Our Codes and Model are been open sourced, available for reproduction: https://github.com/zade90/Agora