一个智能助手同时照顾多人需求，让老人、孩子和特殊人群更平等使用家庭AI。
Plural Voices, Single Agent: Towards Inclusive AI in Multi-User Domestic Spaces
- 单智能体动态协商多方需求，实时对齐价值取向
- 公平性达90%、零安全违规，优于多智能体基线
- 适合家庭场景中关注包容性与伦理的开发者
家庭AI代理在伦理、自主性和包容性方面面临挑战，尤其对儿童、老年人及神经多样性用户群体。我们提出普适声音模型（PVM），一种新型单智能体框架，通过实时价值对齐动态协调多用户需求，利用心理健康、老年护理、教育和道德推理等公开数据集。采用人类+合成课程设计，结合公平导向场景与伦理增强，识别核心价值、冲突与可访问性要求，指导包容性原则。隐私友好的原型具备自适应安全支撑、定制化交互（如为神经多样性用户提供分步引导、为儿童简化用语）和公平冲突解决机制。初步评估显示，PVM在合规性（76% vs. 70%）、公平性（90% vs. 85%）、安全违规率（0% vs. 7%）和延迟方面均优于多智能体基线。设计创新包括视频引导、自主权滑块、家庭枢纽和自适应安全仪表板，为伦理化、包容性的家庭AI提供新方向。代码与模型已开源：https://github.com/zade90/Agora
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。