Towards Automated Crowdsourced Testing via Personified-LLM

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Shengcheng, Ling, Yuchen, Fang, Chunrong, Chen, Zhenyu, Chen, Chunyang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917410153431040
author Yu, Shengcheng
Ling, Yuchen
Fang, Chunrong
Chen, Zhenyu
Chen, Chunyang
author_facet Yu, Shengcheng
Ling, Yuchen
Fang, Chunrong
Chen, Zhenyu
Chen, Chunyang
contents The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven effective in this context by leveraging the diversity of human testers to achieve rich, scenario-based coverage across varied devices, user behaviors, and usage environments. In parallel, automated testing, particularly with the advent of large language models (LLMs), offers significant advantages in controllability, reproducibility, and efficiency, enabling scalable and systematic exploration. However, automated approaches often lack the behavioral diversity characteristic of human testers, limiting their capability to fully simulate real-world testing dynamics. To address this gap, we present PersonaTester, a novel personified-LLM-based framework designed to automate crowdsourced GUI testing. By injecting representative personas, defined along three orthogonal dimensions: testing mindset, exploration strategy, and interaction habit, into LLM-based agents, PersonaTester enables the simulation of diverse human-like testing behaviors in a controllable and repeatable manner. Experimental results demonstrate that PersonaTester faithfully reproduces the behavioral patterns of real crowdworkers, exhibiting strong intra-persona consistency and clear inter-persona variability (117.86% -- 126.23% improvement over the baseline). Moreover, persona-guided testing agents consistently generate more effective test events and trigger more crashes (100+) and functional bugs (11) than the baseline without persona, thus substantially advancing the realism and effectiveness of automated crowdsourced GUI testing.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24160
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Automated Crowdsourced Testing via Personified-LLM
Yu, Shengcheng
Ling, Yuchen
Fang, Chunrong
Chen, Zhenyu
Chen, Chunyang
Software Engineering
The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven effective in this context by leveraging the diversity of human testers to achieve rich, scenario-based coverage across varied devices, user behaviors, and usage environments. In parallel, automated testing, particularly with the advent of large language models (LLMs), offers significant advantages in controllability, reproducibility, and efficiency, enabling scalable and systematic exploration. However, automated approaches often lack the behavioral diversity characteristic of human testers, limiting their capability to fully simulate real-world testing dynamics. To address this gap, we present PersonaTester, a novel personified-LLM-based framework designed to automate crowdsourced GUI testing. By injecting representative personas, defined along three orthogonal dimensions: testing mindset, exploration strategy, and interaction habit, into LLM-based agents, PersonaTester enables the simulation of diverse human-like testing behaviors in a controllable and repeatable manner. Experimental results demonstrate that PersonaTester faithfully reproduces the behavioral patterns of real crowdworkers, exhibiting strong intra-persona consistency and clear inter-persona variability (117.86% -- 126.23% improvement over the baseline). Moreover, persona-guided testing agents consistently generate more effective test events and trigger more crashes (100+) and functional bugs (11) than the baseline without persona, thus substantially advancing the realism and effectiveness of automated crowdsourced GUI testing.
title Towards Automated Crowdsourced Testing via Personified-LLM
topic Software Engineering
url https://arxiv.org/abs/2603.24160