AI助手模仿真人聊天节奏，让群聊互动难辨真假。
Humanlike Multi-user Agent (HUMA): Designing a Deceptively Human AI Facilitator for Group Chats
- 用事件驱动架构模拟人类发消息的随机节奏和互动方式。
- 97人实验中，参与者无法可靠区分AI与真人社区管理员。
- 适合想提升群聊体验的社交平台或客服系统开发者。
基于大语言模型的对话代理正日益普及，但多数系统仍设计为一对一、轮流对话，而非自然的异步群聊。随着AI助手在虚拟助理、客户服务等数字平台广泛应用，模拟真实自然的人类互动模式对维持用户信任与参与度至关重要。本文提出人类化多用户代理（HUMA），一个基于LLM的群聊协作者，采用类人策略与时间模式参与多方对话。HUMA通过事件驱动架构处理消息、回复与点赞，并引入真实响应时间模拟。其由路由器（Router）、行动代理（Action Agent）和反思模块（Reflection）组成，协同适配大模型在群聊动态中的表现。我们在4人角色扮演群聊中开展受控研究，评估97名参与者对AI与真人社区管理者的评价。结果表明，两种条件下参与者对社区管理者是否为人的判断接近随机水平，难以有效区分HUMA与真人。主观体验方面，社区管理有效性、社会存在感及参与度/满意度差异微小，效应量较小。结果表明，在自然群聊场景中，该AI协作者可达到与人类相当的质量，且难以被识别为非人类。
原文摘要 · Abstract (English)
Conversational agents built on large language models (LLMs) are becoming increasingly prevalent, yet most systems are designed for one-on-one, turn-based exchanges rather than natural, asynchronous group chats. As AI assistants become widespread throughout digital platforms, from virtual assistants to customer service, developing natural and humanlike interaction patterns seems crucial for maintaining user trust and engagement. We present the Humanlike Multi-user Agent (HUMA), an LLM-based facilitator that participates in multi-party conversations using human-like strategies and timing. HUMA extends prior multi-user chatbot work with an event-driven architecture that handles messages, replies, reactions and introduces realistic response-time simulation. HUMA comprises three components-Router, Action Agent, and Reflection-which together adapt LLMs to group conversation dynamics. We evaluate HUMA in a controlled study with 97 participants in four-person role-play chats, comparing AI and human community managers (CMs). Participants classified CMs as human at near-chance rates in both conditions, indicating they could not reliably distinguish HUMA agents from humans. Subjective experience was comparable across conditions: community-manager effectiveness, social presence, and engagement/satisfaction differed only modestly with small effect sizes. Our results suggest that, in natural group chat settings, an AI facilitator can match human quality while remaining difficult to identify as nonhuman.
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。