Benchmarking that Matters: Rethinking Benchmarking for Practical Impact

TL;DR

This paper critiques current benchmarking practices in Evolutionary Computation, highlighting their disconnect from real-world problems and proposing a community-driven ecosystem of curated, real-world-inspired benchmarks and tools.

Contribution

It identifies key gaps in current benchmarking methods and proposes a comprehensive vision for a living, evolving benchmarking ecosystem aligned with practical needs.

Findings

Current benchmarks poorly reflect real-world problems

Synthetic suites are misused for industrial decision-making

A community effort can improve benchmarking relevance and impact

Abstract

Benchmarking has driven scientific progress in Evolutionary Computation, yet current practices fall short of real-world needs. Widely used synthetic suites such as BBOB and CEC isolate algorithmic phenomena but poorly reflect the structure, constraints, and information limitations of continuous and mixed-integer optimization problems in practice. This disconnect leads to the misuse of benchmarking suites for competitions, automated algorithm selection, and industrial decision-making, despite these suites being designed for different purposes. We identify key gaps in current benchmarking practices and tooling, including limited availability of real-world-inspired problems, missing high-level features, and challenges in multi-objective and noisy settings. We propose a vision centered on curated real-world-inspired benchmarks, practitioner-accessible feature spaces and community-maintained performance databases. Real progress requires coordinated effort: A living benchmarking ecosystem that evolves with real-world insights and supports both scientific understanding and industrial use.