Let the Barbarians In: How AI Can Accelerate Systems Performance Research

TL;DR

This paper introduces AI-Driven Research for Systems (ADRS), a paradigm where AI automates the discovery and optimization of system performance solutions, demonstrating its effectiveness through multiple case studies and outlining best practices.

Contribution

It presents ADRS as a novel framework for automating systems research, with extensive evaluation and insights into effective implementation strategies.

Findings

ADRS solutions match or outperform human designs in various case studies.

Effective ADRS use depends on prompt specification, feedback, and evaluation practices.

The paper provides best practices and discusses future directions for ADRS in systems research.

Abstract

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.