Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead
Yanqi Su, Zhenchang Xing, Chong Wang, Chunyang Chen, Xiwei Xu, Qinghua Lu, Liming Zhu
TL;DR
This paper investigates automated soap opera testing guided by LLMs and a Scenario Knowledge Graph (SKG) to address limitations of manual exploratory testing for GUI-based software. It first derives insights from a formative study of human testers, then designs a three-agent system (Planner, Player, Detector) that uses multi-modal LLMs and SKG to automate test execution and bug detection. Empirical results show promising feasibility but also notable gaps: automated testing lags behind manual testing in boundary exploration and suffers from false positives, though SKG knowledge and neural-symbolic integration substantially improve performance. The authors propose a road map emphasizing neural-symbolic synergy, human-AI co-learning, and deeper integration with broader software engineering knowledge to advance automated soap opera testing toward practical deployment.
Abstract
Exploratory testing (ET) harnesses tester's knowledge, creativity, and experience to create varying tests that uncover unexpected bugs from the end-user's perspective. Although ET has proven effective in system-level testing of interactive systems, the need for manual execution has hindered large-scale adoption. In this work, we explore the feasibility, challenges and road ahead of automated scenario-based ET (a.k.a soap opera testing). We conduct a formative study, identifying key insights for effective manual soap opera testing and challenges in automating the process. We then develop a multi-agent system leveraging LLMs and a Scenario Knowledge Graph (SKG) to automate soap opera testing. The system consists of three multi-modal agents, Planner, Player, and Detector that collaborate to execute tests and identify potential bugs. Experimental results demonstrate the potential of automated soap opera testing, but there remains a significant gap compared to manual execution, especially under-explored scenario boundaries and incorrectly identified bugs. Based on the observation, we envision road ahead for the future of automated soap opera testing, focusing on three key aspects: the synergy of neural and symbolic approaches, human-AI co-learning, and the integration of soap opera testing with broader software engineering practices. These insights aim to guide and inspire the future research.