Workshops Archive

Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI


Workshop: Thirteenth Workshop on Accelerator Programming and Directives (WACCPD 2026)

Authors: Heyang Thomas Li (REANNZ)

Abstract: Python is widely used in scientific research because it enables rapid development and provides rich ecosystems for data analysis, AI and machine learning. However, customised research code can become prohibitively slow as experiments scale. This challenge is particularly acute in discrete-event project-scheduling simulations, where sequential state updates, nested loops, conditional evaluations, and object-oriented structures limit the benefits of compiled numerical and GPU-accelerated libraries. Addressing these bottlenecks typically requires iterative profiling, refactoring, testing, and validation, yet researchers may lack the time or specialised software-engineering expertise for low-level optimisation. This paper presents a systematic refactoring approach using Claude agentic AI on real-world project-scheduling workloads in a high-performance computing environment. Guided by representative benchmarks and correctness checks, the agent identifies bottlenecks, implements targeted optimisations, and evaluates their effects, while the researcher retains final control. Testing runtime reduced from 1,298 seconds to under 200 seconds without changing outputs, saving four million core-hours (NZ$320,000) annually.


Back to Thirteenth Workshop on Accelerator Programming and Directives (WACCPD 2026) Archive Listing

Back to Full Workshop Archive Listing