让AI悄悄听懂对话，在恰当时候出手帮忙，不打扰也不遗漏。
Overhearing LLM Agents: A Survey, Taxonomy, and Roadmap
- AI持续监听环境对话，仅在合适时机介入提供帮助。
- 提出首个针对此类AI的交互分类体系与开发准则。
- 适合设计无感助手、智能协作者等场景的开发者参考。
设想一种智能助手：它能在不打断对话的情况下提升交流效率——如在医疗会诊中默默提供信息，在教师备课时自动准备材料，或在同事讨论日程时悄然安排会议。尽管当前对话式大模型代理通过聊天界面直接协助人类用户，本文探讨了一种替代范式，即“旁听型代理”（overhearing agents）。这类代理不依赖用户主动请求，而是持续监听周围活动，在具备上下文关联性时才介入辅助。本文首次系统分析了旁听型大模型代理作为人机交互新范式的潜力，并基于对先前大模型代理研究及探索性人机交互实验的调研，建立了一个涵盖交互模式与任务类型的分类体系。在此基础上，提炼出一套面向研究人员和开发者的最佳实践指南。最后，指出了当前研究的空白点，揭示了未来在该范式下的关键机遇。
原文摘要 · Abstract (English)
Imagine AI assistants that enhance conversations without interrupting them: quietly providing relevant information during a medical consultation, seamlessly preparing materials as teachers discuss lesson plans, or unobtrusively scheduling meetings as colleagues debate calendars. While modern conversational LLM agents directly assist human users with tasks through a chat interface, we study this alternative paradigm for interacting with LLM agents, which we call "overhearing agents." Rather than demanding the user's attention, overhearing agents continuously monitor ambient activity and intervene only when they can provide contextual assistance. In this paper, we present the first analysis of overhearing LLM agents as a distinct paradigm in human-AI interaction and establish a taxonomy of overhearing agent interactions and tasks grounded in a survey of works on prior LLM-powered agents and exploratory HCI studies. Based on this taxonomy, we create a list of best practices for researchers and developers building overhearing agent systems. Finally, we outline the remaining research gaps and reveal opportunities for future research in the overhearing paradigm.
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。