# Harness Engineering for LLM-Driven GPU Kernel Generation

arXiv: https://arxiv.org/abs/2607.17979 · HTML: https://mlsanity.com/paper/2607.17979/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems](https://mlsanity.com/paper/2601.00227/) (2026)
- [AVO: Agentic Variation Operators for Autonomous Evolutionary Search](https://mlsanity.com/paper/2603.24517/) (2026)
- [LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm](https://mlsanity.com/paper/2512.24077/) (2025)
- [AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search](https://mlsanity.com/paper/2603.21331/) (2026)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)

## Built on by (most cited first, 2 of 2)

- [KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?](https://mlsanity.com/paper/2607.27231/) (2026)
- [D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?](https://mlsanity.com/paper/2610.03226/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected. This paper presents a harness-centered system for LLM-driven GPU kernel optimization in the MLSys 2026 FlashInfer AI Kernel Generation Contest on NVIDIA Blackwell B200 GPUs. The system separates an evaluation harness from a profile-backed optimization controller: the harness enforces compilation, correctness, official-aligned timing, and artifact archival, while the controller turns profiler and workload evidence into bounded candidate-generation decisions. Human-authored skills capture operator constraints, references, profiling procedures, and promotion rules, while Codex and Claude Code agents generate candidate kernels inside those constraints. Across five operator definitions, the retained official-aligned artifacts achieved mean-latency speedups over supplied FlashInfer baselines of 1.62x, 18.05x, 29.68x, 1.12x, and 13.70x. The Agent-Assisted kernels outperform the Full-Agent artifacts across the evaluated definitions, indicating that expert-provided optimization directions, high-quality references, and workload context remain critical for reliable AI-driven kernel optimization.