# PassNet: Scaling Large Language Models for Graph Compiler Pass Generation

arXiv: https://arxiv.org/abs/2605.29357 · HTML: https://mlsanity.com/paper/2605.29357/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 22 of 22)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [Kevin: Multi-Turn RL for Generating CUDA Kernels](https://mlsanity.com/paper/2507.11948/) (2025)
- [A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends](https://mlsanity.com/paper/2311.10372/) (2023)
- [CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2507.14111/) (2025)
- [CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation](https://mlsanity.com/paper/2602.24286/) (2026)
- [The Deep Learning Compiler: A Comprehensive Survey](https://mlsanity.com/paper/2002.03794/) (2020)
- [CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research](https://mlsanity.com/paper/2109.08267/) (2021)
- [Tensor Program Optimization with Probabilistic Programs](https://mlsanity.com/paper/2205.13603/) (2022)
- [Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs](https://mlsanity.com/paper/2210.09603/) (2022)
- [STARK: Strategic Team of Agents for Refining Kernels](https://mlsanity.com/paper/2510.16996/) (2025)
- [TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs](https://mlsanity.com/paper/2308.13490/) (2023)
- [TLP: A Deep Learning-based Cost Model for Tensor Program Tuning](https://mlsanity.com/paper/2211.03578/) (2022)
- [MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning](https://mlsanity.com/paper/2404.12636/) (2024)
- [Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing](https://mlsanity.com/paper/2506.16136/) (2025)
- [ComPile: A Large IR Dataset from Production Sources](https://mlsanity.com/paper/2309.15432/) (2023)
- [Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning](https://mlsanity.com/paper/2506.15701/) (2025)

## Built on by (most cited first, 1 of 1)

- [Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills](https://mlsanity.com/paper/2609.02749/) (2026)

## Abstract (arXiv)

Modern tensor compilers such as TorchInductor deliver substantial speedups on mainstream models, yet face a systematic performance ceiling on long-tail workloads -- our profiling shows that 43% of real-world subgraphs experience end-to-end slowdowns under default compilation. While LLMs offer a path toward automated optimization, existing efforts focus on standalone kernel generation. We argue that pass generation -- where LLMs author structured graph transformations that integrate directly into compiler pipelines -- is the more appropriate abstraction. We propose PassNet, the first large-scale ecosystem for LLM-based compiler pass generation, comprising: (1) PassNet-Dataset, over 18K unique computational graphs from 100K real-world models; and (2) PassBench, 200 curated long-tail fusible tasks (comprising 2,060 subgraphs in total) evaluated under the Error-aware Speedup Score (ES_t) -- a metric unifying correctness, stability, and performance -- with layered integrity defenses against systematic LLM exploitation. Experiments reveal that PassBench is both highly discriminative and genuinely unsaturated: the best frontier model trails TorchInductor by 37% in aggregate, yet on individual subgraphs LLMs achieve up to 3x speedup over the same compiler -- indicating that the bottleneck is consistency, not capability. Fine-tuning a small model on merely ~4K PassNet trajectories yields a 2.67x improvement approaching frontier-model performance, demonstrating substantial headroom and validating PassNet as live training infrastructure for advancing LLM-driven compiler optimization. All data, benchmarks, and tooling are publicly available.