# AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs

arXiv: https://arxiv.org/abs/2507.05687 · HTML: https://mlsanity.com/paper/2507.05687/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators](https://mlsanity.com/paper/2502.14752/) (2025)
- [Seed-Coder: Let the Code Model Curate Data for Itself](https://mlsanity.com/paper/2506.03524/) (2025)
- [CYCLE: Learning to Self-Refine the Code Generation](https://mlsanity.com/paper/2403.18746/) (2024)

## Built on by (most cited first, 30 of 40)

- [MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation](https://mlsanity.com/paper/2507.17773/) (2025)
- [TritonRL: Training LLMs to Think and Code Triton Without Cheating](https://mlsanity.com/paper/2510.17891/) (2025)
- [K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model](https://mlsanity.com/paper/2602.19128/) (2026)
- [Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations](https://mlsanity.com/paper/2602.05885/) (2026)
- [ConCuR: Conciseness Makes State-of-the-Art Kernel Generation](https://mlsanity.com/paper/2510.07356/) (2025)
- [KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels](https://mlsanity.com/paper/2605.04956/) (2026)
- [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)
- [AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis](https://mlsanity.com/paper/2512.23424/) (2025)
- [AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation](https://mlsanity.com/paper/2601.22760/) (2026)
- [Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization](https://mlsanity.com/paper/2603.28342/) (2026)
- [CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe](https://mlsanity.com/paper/2604.01489/) (2026)
- [From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training](https://mlsanity.com/paper/2511.07738/) (2025)
- [KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta](https://mlsanity.com/paper/2512.23236/) (2025)
- [KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware](https://mlsanity.com/paper/2603.08721/) (2026)
- [CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution](https://mlsanity.com/paper/2608.12629/) (2026)
- [DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels](https://mlsanity.com/paper/2602.11715/) (2026)
- [OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization](https://mlsanity.com/paper/2602.12305/) (2026)
- [Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis](https://mlsanity.com/paper/2603.10846/) (2026)
- [DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation](https://mlsanity.com/paper/2603.21465/) (2026)
- [AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization](https://mlsanity.com/paper/2603.23566/) (2026)
- [AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation](https://mlsanity.com/paper/2604.16625/) (2026)
- [FastKernels: Benchmarking GPU Kernel Generation in Production](https://mlsanity.com/paper/2605.23215/) (2026)
- [daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization](https://mlsanity.com/paper/2606.16497/) (2026)
- [AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents](https://mlsanity.com/paper/2605.16819/) (2026)
- [Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU](https://mlsanity.com/paper/2605.26118/) (2026)
- [MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU](https://mlsanity.com/paper/2606.04847/) (2026)
- [RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks](https://mlsanity.com/paper/2608.12004/) (2026)
- [MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?](https://mlsanity.com/paper/2603.11935/) (2026)
- [From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation](https://mlsanity.com/paper/2606.16231/) (2026)

## Abstract (arXiv)

Kernel development in deep learning requires optimizing computational units across hardware while balancing memory management, parallelism, and hardware-specific optimizations through extensive empirical tuning. Although domain-specific languages like Triton simplify GPU programming by abstracting low-level details, developers must still manually tune critical parameters such as tile sizes and memory access patterns through iterative experimentation, creating substantial barriers to optimal performance and wider adoption. In this work, we introduce AutoTriton, the first model dedicated to Triton programming powered by reinforcement learning (RL). AutoTriton performs supervised fine-tuning (SFT) to be equipped with essential Triton programming expertise using a high-quality data gathering pipeline, and conducts RL with Group Relative Policy Optimization (GRPO) algorithm, combining a rule-based reward and an execution-based reward to further improve Triton programming ability, sequentially. Experiments across five evaluation channels of TritonBench and KernelBench illustrate that our 8B model AutoTriton achieves performance comparable to mainstream large models, including Claude-4-Sonnet and DeepSeek-R1-0528. Further experimental analysis demonstrates the crucial role of each module within AutoTriton, including the SFT stage, the RL stage, and the reward design strategy. These findings underscore the promise of RL for automatically generating high-performance kernels, and since high-performance kernels are core components of AI systems, this breakthrough establishes an important foundation for building more efficient AI systems. The model and code will be available at https://github.com/AI9Stars/AutoTriton.