Plural Voices, Single Agent: Towards Inclusive AI in Multi-User Domestic Spaces

TL;DR

This paper introduces the Plural Voices Model (PVM), a single-agent framework designed to negotiate multi-user needs in domestic AI, emphasizing inclusivity, ethical considerations, and real-time value alignment for diverse user groups.

Contribution

The paper presents a novel single-agent approach that dynamically manages multi-user needs and conflicts in domestic AI, incorporating fairness, safety, and accessibility through innovative design and evaluation.

Findings

PVM outperforms multi-agent baselines in compliance and fairness.

PVM achieves a 0% safety-violation rate in preliminary tests.

Design features like video guidance and adaptive safety enhance inclusivity.

Abstract

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