AI RESEARCH
PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation
arXiv CS.LG
•
ArXi:2605.00942v1 Announce Type: cross Developing effective test cases capable of thoroughly exercising large-scale software systems is inherently difficult, especially if such systems have voluminous, complex, and deeply nested source codes. In this work, we present a novel approach for generating test cases using a reinforcement learning-driven agentic framework where Proximal Policy Optimization (PPO) is coupled with an LLM engine to guide prompt selection during test generation. Our approach consists of two phases.