AI 中文总结
针对可穿戴健康复合查询，提出任务导向多智能体框架，通过意图分解与专门智能体提升检索准确率并降低令牌消耗，初步验证其有效性。
AI 中文摘要
可穿戴健康问题通常涉及对结构化记录的数据检索、纵向分析和健康建议。使用单个大型语言模型处理完整记录和复合查询，难以判断每个请求是否被执行以及哪些证据支持答案。我们提出了一种任务导向的多智能体框架，将复合查询表示为不同的意图和带有显式意图内依赖关系的类型化任务。专门的智能体执行检索、分析和建议任务；隔离的意图状态在聚合前保留请求边界和证据关系。我们在一个包含10,000名虚拟用户、一个月纵向可穿戴记录的合成数据集上评估该框架，涵盖结构化数据检索、多意图识别和整体响应质量。在1,500个检索问题中，查询智能体达到了98.3%的准确率，而直接LLM基线为97.9%，同时将查询阶段的平均令牌消耗从6,869减少到3,136。在180个多意图问题中，管理智能体实现了100.0%的多意图覆盖率和94.4%的多集Jaccard相似度。在当前合成评估设置下，我们的方法在两类问题上均获得了更高的平均可信度和透明度得分，而可操作性并未持续改善。这些结果初步表明，显式的任务组织可以支持任务相关的数据访问和基于数据的纵向分析，而将真实可穿戴数据上的健康建议生成和验证留作开放挑战。
英文摘要
Wearable health questions often combine data retrieval, longitudinal analysis, and health advice over structured records. Prompting a single large language model with a complete record and a composite query obscures whether every request is executed and which evidence supports the answer. We propose a task-oriented multi-agent framework that represents a composite query as distinct intents and typed tasks with explicit intra-intent dependencies. Specialized agents execute retrieval, analysis, and advice tasks; isolated intent states preserve request boundaries and evidence relationships before aggregation. We evaluate the framework on a synthetic dataset of $10{,}000$ virtual users with one month of longitudinal wearable records, covering structured data retrieval, multi-intent recognition, and overall response quality. Across $1{,}500$ retrieval questions, the Query Agent achieves $98.3\%$ accuracy, compared with $97.9\%$ for the Direct LLM baseline, while reducing average query-stage token consumption from $6{,}869$ to $3{,}136$. On $180$ multi-intent questions, the Manager Agent achieves $100.0\%$ Multi-Intent Coverage and $94.4\%$ Multiset Jaccard Similarity. Under the current synthetic evaluation setting, our method receives higher mean Trustworthiness and Transparency scores on both question categories, whereas Actionability does not improve consistently. These results provide preliminary evidence that explicit task organization can support task-relevant data access and data-grounded longitudinal analysis, while leaving health advice generation and validation on real wearable data as open challenges.
Comments23 pages, 4 figures. Code available at https://github.com/yangkunpeng-coder/WearableDeviceAgents-paper
