arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.26107cs.HCcs.AI
收藏

一个不够:人们如何在日常生活中使用多个AI模型

One Is Not Enough: How People Use Multiple AI Models in Everyday Life

KAIST(韩国科学技术院)

Seunghwa Pyo, Donggun Lee, Jungwoo Rhee, Soobin Park, Youn-kyung Lim

AI总结:

研究探讨了人们如何在日常生活中协调多个多模态大语言模型,揭示用户构建模型层级和切换策略以优化任务效率与输出可信度。

摘要:

人们越来越多地同时使用多个多模态大语言模型(MLLMs),根据其感知优势进行选择。这种跨平台实践带来了协调挑战:适应不同界面的提示、校准信任以应对不一致行为,以及导航各自的历史对话。以往的人机交互(HCI)研究聚焦于单个智能体交互,多MLLM协同调度仍被忽视。通过日记研究和半结构化访谈(N=10),我们探讨了个体如何在竞争的AI系统中组织工作。我们的发现表明,用户在模型之间构建主次层级,这些层级会随使用情境变化。他们还发展出个性化的切换模式,通过任务聚合来调整努力和延迟,并输出可信度。这些见解为未来工具设计提供了机会,支持用户协调多MLLM工作流程。

英文摘要:

People increasingly use multiple Multimodal Large Language Models (MLLMs) concurrently, selecting each based on its perceived strengths. This cross-platform practice creates coordination challenges: adapting prompts to different interfaces, calibrating trust against inconsistent behaviors, and navigating separate conversation histories. Prior HCI research focused on single-agent interactions, leaving multi-MLLM orchestration underexplored. Through a diary study and semi-structured interviews (N=10), we examine how individuals organize work across competing AI systems. Our findings reveal that users construct primary and secondary hierarchies among models that shift over usage context. They also develop personalized switching patterns triggered by task aggregation to adjust effort and latency, and output credibility. These insights inform future tool design opportunities, supporting users to coordinate multi-MLLM workflows.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑