# CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language

arXiv: https://arxiv.org/abs/2609.00058 · HTML: https://mlsanity.com/paper/2609.00058/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2507.14111/) (2025)
- [Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity](https://mlsanity.com/paper/2607.00248/) (2026)
- [LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?](https://mlsanity.com/paper/2506.11928/) (2025)
- [CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation](https://mlsanity.com/paper/2602.24286/) (2026)
- [CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization](https://mlsanity.com/paper/2511.01884/) (2025)
- [CUDA-LLM: LLMs Can Write Efficient CUDA Kernels](https://mlsanity.com/paper/2506.09092/) (2025)
- [STARK: Strategic Team of Agents for Refining Kernels](https://mlsanity.com/paper/2510.16996/) (2025)
- [QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation](https://mlsanity.com/paper/2511.20100/) (2025)
- [ConCuR: Conciseness Makes State-of-the-Art Kernel Generation](https://mlsanity.com/paper/2510.07356/) (2025)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)
- [KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization](https://mlsanity.com/paper/2603.10085/) (2026)
- [From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph](https://mlsanity.com/paper/2510.19873/) (2025)
- [CUDABench: Benchmarking LLMs for Text-to-CUDA Generation](https://mlsanity.com/paper/2603.02236/) (2026)
- [cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution](https://mlsanity.com/paper/2512.16465/) (2025)
- [Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization](https://mlsanity.com/paper/2603.28342/) (2026)

## Abstract (arXiv)

Developing high-performance CUDA kernels demands specialized knowledge in algorithm implementation, correctness validation, and hardware-aware parallel optimization, creating a substantial expertise barrier and making generating CUDA kernels directly from natural language (Text2CUDA) essential. Meanwhile, the general-purpose code generation capability of Large Language Models (LLMs) prompts a series of works exploring LLM-based CUDA kernel generation. They mainly focus on transpilation from high-level frameworks such as PyTorch to CUDA (Torch2CUDA) rather than Text2CUDA, where models must understand the high-level input semantics and handle low-level kernel implementation and validation. Additionally, these methods are vulnerable to reward hacking due to reliance on predefined test inputs. In this paper, we propose CUDA-Harness, a framework for harnessing agentic CUDA kernel generation and optimization from natural language. Specifically, we introduce Intermediate-Structured Generation to connect high-level semantic understanding with low-level kernel generation. To dilute reward hacking in Text2CUDA, we construct Synthesis-Based Verification to provide isolated test data and progressive validation. Furthermore, we propose Feedback-Adaptive Evolution, a kernel evolution strategy that prioritizes correctness while optimizing performance. Finally, through extensive experiments, we demonstrate the effectiveness of CUDA-Harness, with further evaluations illustrating generalization across LLMs, hardware platforms, and to C-to-CUDA transpilation.