# AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

arXiv: https://arxiv.org/abs/2606.20373 · HTML: https://mlsanity.com/paper/2606.20373/

## Key facts

- Cited by 1 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 19 of its 46 references that are in the map.
- First posted on arXiv 18 Jun 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, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research](https://mlsanity.com/paper/2109.08267/) (2021)
- [A Survey on Compiler Autotuning using Machine Learning](https://mlsanity.com/paper/1801.04405/) (2018)
- [MLGO: a Machine Learning Guided Compiler Optimizations Framework](https://mlsanity.com/paper/2101.04808/) (2021)
- [Meta Large Language Model Compiler: Foundation Models of Compiler Optimization](https://mlsanity.com/paper/2407.02524/) (2024)
- [CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation](https://mlsanity.com/paper/2501.07811/) (2025)
- [SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly](https://mlsanity.com/paper/2305.12520/) (2023)
- [Search-Based LLMs for Code Optimization](https://mlsanity.com/paper/2408.12159/) (2024)
- [LLM-Vectorizer: LLM-based Verified Loop Vectorizer](https://mlsanity.com/paper/2406.04693/) (2024)
- [CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System](https://mlsanity.com/paper/2505.04254/) (2025)
- [AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning](https://mlsanity.com/paper/1901.04615/) (2019)
- [The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-Based Code Generation](https://mlsanity.com/paper/2411.06774/) (2024)
- [ResTest: Targeted Coverage of Residual Not-Covered Code Using Large Language Models for Web GUI Testing](https://mlsanity.com/paper/2506.00520/) (2025)
- [Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning](https://mlsanity.com/paper/2506.15701/) (2025)
- [WaDec: Decompiling WebAssembly Using Large Language Model](https://mlsanity.com/paper/2406.11346/) (2024)
- [A Collaborative Filtering Approach for the Automatic Tuning of Compiler Optimisations](https://mlsanity.com/paper/2005.04092/) (2020)
- [AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework](https://mlsanity.com/paper/2510.11759/) (2025)
- [Hardware Counted Profile-Guided Optimization](https://mlsanity.com/paper/1411.6361/) (2014)

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

- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning schemes, AutoPass opens up the compiler to the LLM, enabling it to query compiler-internal optimization states and analyze the intermediate representation to orchestrate compiler options. The search process iteratively refines optimization configurations using measured runtime feedback to diagnose regressions and guide latency-improving edits. AutoPass operates in an inference-only, training-free setting and requires no offline training or task-specific fine-tuning, making it readily applicable to new benchmarks and platforms. We implement AutoPass on the LLVM compiler and evaluate it on server-grade x86-64 and embedded ARM64 systems. AutoPass outperforms expert-tuned heuristics and classical autotuning methods, achieving geometric-mean speedups of 1.043x and 1.117x over LLVM -O3 on x86-64 and ARM64, respectively.