Conversational Health Agents (CHAs) are interactive systems designed to
enhance personal healthcare services by engaging in empathetic conversations
and processing multimodal data. While current CHAs, especially those utilizing
Large Language Models (LLMs), primarily focus on conversation, they often lack
comprehensive agent capabilities. This includes the ability to access personal
user health data from wearables, 24/7 data collection sources, and electronic
health records, as well as integrating the latest published health insights and
connecting with established multimodal data analysis tools. We are developing a
framework to empower CHAs by equipping them with critical thinking, knowledge
acquisition, and problem-solving abilities. Our CHA platform, powered by LLMs,
seamlessly integrates healthcare tools, enables multilingual and multimodal
conversations, and interfaces with a variety of user data analysis tools. We
illustrate its proficiency in handling complex healthcare tasks, such as stress
level estimation, showcasing the agent's cognitive and operational
capabilities.

我们正在开发一个框架，通过赋予对话健康代理（CHAs）关键思维、知识获取和问题解决能力，以增强个人医疗保健服务，并展示其在处理复杂医疗任务中的熟练性和操作能力。