Utilizing LLMs for Deep Reinforcement Learning States and Bug Detection in Clickable Elements of Web Applications

Read full text Summarise with VIRAT
Authors: Yuki SAKAI, Yasuyuki Tahara, Akihiko Ohsuga, Yuichi Sei
Cited by: 0
References: 26

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper proposes a method for utilizing large language model (LLM) inference results in the state space of deep reinforcement learning (DRL)-based GUI black-box testing for web applications. Previous research on mobile applications has shown that using HTML element interaction information in training improves the exploration performance of DRL agents. However, in web applications, obtaining interaction information can be difficult depending on the browser. Therefore, this study proposes a method that uses an LLM to infer clickability of elements, that is, one example of interaction information, from HTML and utilizes these results as part of the DRL state. Through experiments on a simple web application, we confirmed that using LLM-inferred values as state information improved learning efficiency and accuracy. Similar results were also demonstrated in experiments targeting a complex web application. The findings of this research enable browser-independent automation of GUI black-box testing and present a novel approach to utilizing LLMs for obtaining DRL states.

Fields of Study & Subjects

Software Testing and Debugging Techniques Web Data Mining and Analysis Robotic Process Automation Applications

Publication details

Journal / source
IEICE Transactions on Information and Systems
Volume
E109.D
Issue
9
Pages
1498–1511
Publication date
22 March 2026
Language
EN