arXiv cs.AI· Seunghwa Pyo, Donggun Lee, Jungwoo Rhee, Soobin Park, Youn-kyung Lim·· 3 天前AI 评分20
一项 CHI 2026 研究：人们如何在日常生活中同时使用多个 AI 模型
One Is Not Enough: How People Use Multiple AI Models in Everyday Life
AI 导读
一项日记研究与半结构化访谈（N=10）考察了人们如何在多个多模态大语言模型（MLLM）之间组织日常工作。用户会在模型中建立随使用场景变化的主次层级，并形成由任务聚合触发的个性化切换模式，以调节投入、延迟与输出可信度。研究指出，现有 HCI 研究多聚焦单一智能体交互，多 MLLM 协同编排仍待探索。
正文 · 原文
Abstract: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.
| Comments: | Accepted as a poster at CHI 2026 |
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.26107 [cs.HC] |
| (or arXiv:2603.26107v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2603.26107 arXiv-issued DOI via DataCite |
Submission history
From: Seunghwa Pyo [view email]
[v1]
Fri, 27 Mar 2026 06:33:30 UTC (445 KB)
来源：arXiv cs.AI · arxiv.org