# CompileRover: Revolutionizing Virtual Machine Compiler Optimization with a Tri-Role LLM-Driven Framework

arXiv: https://arxiv.org/abs/2609.19004 · HTML: https://mlsanity.com/paper/2609.19004/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design](https://mlsanity.com/paper/2501.08603/) (2025)
- [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)
- [Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy](https://mlsanity.com/paper/2501.15167/) (2025)
- [Static Neural Compiler Optimization via Deep Reinforcement Learning](https://mlsanity.com/paper/2008.08951/) (2020)
- [PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference](https://mlsanity.com/paper/2509.04467/) (2025)
- [TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts](https://mlsanity.com/paper/2512.22748/) (2025)
- [Multimodal Multi-Agent Empowered Legal Judgment Prediction](https://mlsanity.com/paper/2601.12815/) (2026)
- [Demystifying Flux Architecture](https://mlsanity.com/paper/2507.09595/) (2025)
- [Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning](https://mlsanity.com/paper/2602.01745/) (2026)
- [Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?](https://mlsanity.com/paper/2510.12087/) (2025)
- [ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code](https://mlsanity.com/paper/2601.20679/) (2026)
- [CompilerDream: Learning a Compiler World Model for General Code Optimization](https://mlsanity.com/paper/2404.16077/) (2024)
- [GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2511.00908/) (2025)
- [Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis](https://mlsanity.com/paper/2602.16144/) (2026)
- [LEGO-Compiler: Enhancing Neural Compilation Through Translation Composability](https://mlsanity.com/paper/2505.20356/) (2025)

## Abstract (arXiv)

Code optimization plays a crucial role in the development of virtual machine compilers, with optimization frameworks significantly enhancing the performance of generated assembly code. However, existing virtual machine compiler outputs frequently exhibit redundant computations, inefficient loop structures, and suboptimal function implementations, which collectively impair execution efficiency. To address these shortcomings, we propose CompileRover, an advanced optimization framework specifically designed for virtual machine compilers. CompileRover employs a sophisticated three-role collaboration mechanism, comprising a referee, an advisor, and an operator, effectively overcoming performance bottlenecks by leveraging comprehensive optimization algorithms and novel methodologies, including control flow analysis, code structure transformations, and dynamic execution pattern recognition. Extensive evaluations demonstrate that CompileRover consistently surpasses state-of-the-art virtual machine compilers, achieving significant improvements in execution performance across various benchmarks. Furthermore, performance analyses validate that the introduced optimizations notably reduce execution overhead, improve dataflow consistency, and robustly enhance compiler performance, showcasing CompileRover as an effective and reliable approach to optimizing virtual machine compilers.