# GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization

arXiv: https://arxiv.org/abs/2506.20807 · HTML: https://mlsanity.com/paper/2506.20807/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 25 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [TileLang: A Composable Tiled Programming Model for AI Systems](https://mlsanity.com/paper/2504.17577/) (2025)

## Built on by (most cited first, 22 of 22)

- [Astra: A Multi-Agent System for GPU Kernel Performance Optimization](https://mlsanity.com/paper/2509.07506/) (2025)
- [AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search](https://mlsanity.com/paper/2603.21331/) (2026)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models](https://mlsanity.com/paper/2510.03760/) (2025)
- [SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization](https://mlsanity.com/paper/2508.20258/) (2025)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)
- [cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution](https://mlsanity.com/paper/2512.16465/) (2025)
- [Improving Coherence and Persistence in Agentic AI for System Optimization](https://mlsanity.com/paper/2603.21321/) (2026)
- [Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance](https://mlsanity.com/paper/2603.29010/) (2026)
- [Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2511.16964/) (2025)
- [Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization](https://mlsanity.com/paper/2606.26453/) (2026)
- [GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs](https://mlsanity.com/paper/2512.22147/) (2025)
- [AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization](https://mlsanity.com/paper/2603.23566/) (2026)
- [AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs](https://mlsanity.com/paper/2604.08590/) (2026)
- [Integrating Performance Tools in Model Reasoning for GPU Kernel Optimization](https://mlsanity.com/paper/2510.17158/) (2025)
- [Automated Design Optimization via Strategic Search with Large Language Models](https://mlsanity.com/paper/2511.22651/) (2025)
- [Unlocking LLM Code Correction with Iterative Feedback Loops](https://mlsanity.com/paper/2606.17514/) (2026)
- [CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits](https://mlsanity.com/paper/2607.20518/) (2026)
- [Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents](https://mlsanity.com/paper/2603.19375/) (2026)
- [MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithms](https://mlsanity.com/paper/2608.24946/) (2026)
- [RoofLang: Enabling AI-Driven Architecting of LLM Inference Systems](https://mlsanity.com/paper/2609.12551/) (2026)
- [How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach?](https://mlsanity.com/paper/2609.21058/) (2026)

## Abstract (arXiv)

Optimizing GPU kernels for high performance is a complex task, often demanding deep architectural knowledge, extensive profiling, and iterative experimentation. This challenge is amplified when targeting newer or less-documented GPU architectures where traditional development aids are scarce. This paper introduces an LLM-powered "GPU Kernel Scientist," an automated methodology for iteratively refining accelerator kernels. Our methodology employs LLMs in a multi-stage, evolutionary process: (a) strategically selecting promising prior code versions as a basis for new iterations; (b) generating hypotheses for optimization experiments, based on existing code and assimilated knowledge from general GPU literature; and (c) autonomously implementing these experiments through code modification and subsequent submission to an external evaluation system, using only observed timing data as performance feedback. We detail how this approach navigates the challenges of the AMD MI300 target architecture and leverages LLMs to compensate for limited domain-specific human expertise. In addition to our results, we present the architectural design, operational workflow, and qualitative insights, highlighting the potential of LLM-driven agents to democratise and accelerate GPU kernel optimization, especially in resource-constrained or rapidly updating hardware environment.