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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pyo, Seunghwa, Lee, Donggun, Rhee, Jungwoo, Park, Soobin, Lim, Youn-kyung
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911547980251136
author Pyo, Seunghwa
Lee, Donggun
Rhee, Jungwoo
Park, Soobin
Lim, Youn-kyung
author_facet Pyo, Seunghwa
Lee, Donggun
Rhee, Jungwoo
Park, Soobin
Lim, Youn-kyung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26107
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle One Is Not Enough: How People Use Multiple AI Models in Everyday Life
Pyo, Seunghwa
Lee, Donggun
Rhee, Jungwoo
Park, Soobin
Lim, Youn-kyung
Human-Computer Interaction
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.
title One Is Not Enough: How People Use Multiple AI Models in Everyday Life
topic Human-Computer Interaction
url https://arxiv.org/abs/2603.26107