# cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

arXiv: https://arxiv.org/abs/2512.16465 · HTML: https://mlsanity.com/paper/2512.16465/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 12 of 12)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models](https://mlsanity.com/paper/2311.16543/) (2023)
- [Kevin: Multi-Turn RL for Generating CUDA Kernels](https://mlsanity.com/paper/2507.11948/) (2025)
- [CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2507.14111/) (2025)
- [AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs](https://mlsanity.com/paper/2507.05687/) (2025)
- [CUDA-LLM: LLMs Can Write Efficient CUDA Kernels](https://mlsanity.com/paper/2506.09092/) (2025)
- [GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization](https://mlsanity.com/paper/2506.20807/) (2025)
- [Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction](https://mlsanity.com/paper/2504.14557/) (2025)
- [SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization](https://mlsanity.com/paper/2508.20258/) (2025)
- [Insights from Rights and Wrongs: A Large Language Model for Solving Assertion Failures in RTL Design](https://mlsanity.com/paper/2503.04057/) (2025)
- [ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection](https://mlsanity.com/paper/2505.19734/) (2025)

## Built on by (most cited first, 7 of 7)

- [KernelFoundry: Hardware-aware evolutionary GPU kernel optimization](https://mlsanity.com/paper/2603.12440/) (2026)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)
- [StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning](https://mlsanity.com/paper/2603.02637/) (2026)
- [Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization](https://mlsanity.com/paper/2606.26453/) (2026)
- [Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation](https://mlsanity.com/paper/2605.26720/) (2026)
- [KernelBrain: Coarse-to-Fine, Budget-Aware Search for Agentic GPU Kernel Optimization](https://mlsanity.com/paper/2608.02611/) (2026)
- [CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language](https://mlsanity.com/paper/2609.00058/) (2026)

## Abstract (arXiv)

Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While recent large language models (LLMs) combined with evolutionary algorithms show promise in automatic kernel optimization, existing approaches often fall short in performance due to their suboptimal agent designs and mismatched evolution representations. This work identifies these mismatches and proposes cuPilot, a strategy-coordinated multi-agent framework that introduces strategy as an intermediate semantic representation for kernel evolution. Key contributions include a strategy-coordinated evolution algorithm, roofline-guided prompting, and strategy-level population initialization. Experimental results show that the generated kernels by cuPilot achieve an average speed up of 3.09× over PyTorch on a benchmark of 100 kernels. On the GEMM tasks, cuPilot showcases sophisticated optimizations and achieves high utilization of critical hardware units. The generated kernels are open-sourced at https://github.com/champloo2878/cuPilot-Kernels.git.