Towards Autonomous Testing Agents via Conversational Large Language Models

TL;DR

This paper explores the use of conversational large language models as autonomous testing agents, proposing a taxonomy, demonstrating practical benefits, and discussing potential limitations and advantages in software testing.

Contribution

It introduces a taxonomy of LLM-based testing agents based on their autonomy level and demonstrates how conversational frameworks can enhance testing processes.

Findings

LLM-based testing agents can improve testing efficiency.

Higher autonomy levels in testing agents offer practical benefits.

Conversational LLMs can utilize hallucinations beneficially in testing.

Abstract

Software testing is an important part of the development cycle, yet it requires specialized expertise and substantial developer effort to adequately test software. Recent discoveries of the capabilities of large language models (LLMs) suggest that they can be used as automated testing assistants, and thus provide helpful information and even drive the testing process. To highlight the potential of this technology, we present a taxonomy of LLM-based testing agents based on their level of autonomy, and describe how a greater level of autonomy can benefit developers in practice. An example use of LLMs as a testing assistant is provided to demonstrate how a conversational framework for testing can help developers. This also highlights how the often criticized hallucination of LLMs can be beneficial for testing. We identify other tangible benefits that LLM-driven testing agents can bestow, and also discuss potential limitations.