Reinforcement Learning for Dynamic Workflow Optimization in CI/CD Pipelines

TL;DR

This paper introduces a reinforcement learning approach to dynamically optimize CI/CD workflows, significantly improving throughput and reducing testing time while maintaining low defect miss rates.

Contribution

It presents a novel RL-based method for adaptive CI/CD pipeline optimization, modeling workflows as a Markov Decision Process and demonstrating practical benefits.

Findings

Up to 30% increase in throughput

Approximately 25% reduction in test execution time

Maintains defect miss rate below 5%

Abstract

Continuous Integration and Continuous Deployment (CI/CD) pipelines are central to modern software delivery, yet their static workflows often introduce inefficiencies as systems scale. This paper proposes a reinforcement learning (RL) based approach to dynamically optimize CI/CD pipeline workflows. The pipeline is modeled as a Markov Decision Process, and an RL agent is trained to make runtime decisions such as selecting full, partial, or no test execution in order to maximize throughput while minimizing testing overhead. A configurable CI/CD simulation environment is developed to evaluate the approach across build, test, and deploy stages. Experimental results show that the RL optimized pipeline achieves up to a 30 percent improvement in throughput and approximately a 25 percent reduction in test execution time compared to static baselines, while maintaining a defect miss rate below 5 percent. The agent learns to selectively skip or abbreviate tests for low risk commits, accelerating feedback cycles without significantly increasing failure risk. These results demonstrate the potential of reinforcement learning to enable adaptive and intelligent DevOps workflows, providing a practical pathway toward more efficient, resilient, and sustainable CI/CD automation.