Logo image
An Agent-Based Approach to Automating Software Performance Testing (Work In Progress Paper)
Conference proceeding   Open access   Peer reviewed

An Agent-Based Approach to Automating Software Performance Testing (Work In Progress Paper)

E Binder, Xiaozhou Li and A Janes
ICPE Companion '26: Companion of the 17th ACM/SPEC International Conference on Performance Engineering, pp.55-61
the 17th ACM/SPEC International Conference on Performance Engineering (Florence, 04/05/2026–08/05/2026)
2026
Handle:
https://hdl.handle.net/10863/52249

Abstract

Performance Testing Microservices Agentic AI Load testing
Performance testing is essential for contemporary software systems because it ensures reliability and user satisfaction (while keeping operational costs under control). Conventional performance testing activities still require expert knowledge, laborious scripting, and substantial time investment within modern DevOps workflows. Recent advances in generative and agentic AI create the opportunity to automate these processes. This work-in-progress paper explores the use of agentic AI to support end-to-end automation of software performance testing. We present an initial prototype that coordinates multiple specialized agents to extract contextual information from existing project artifacts, generate realistic performance test scenarios, execute tests using an established performance testing framework, and provide structured interpretations of the resulting metrics. We report early results from exploratory case studies of microservice-based systems from the DeathStarBench benchmark suite, which suggest that agentic workflows can autonomously produce executable performance tests and meaningful performance reports with limited human intervention, even when available context is incomplete or partially misleading. Such results illustrate the feasibility of agent-based performance testing and motivate a broader research agenda on AI-augmented performance engineering.
pdf
3777911.3801107967.27 kBDownloadView
Open Access
url
https://doi.org/10.1145/3777911.3801107View

Details

Metrics

1 Record Views
Logo image