LLM-VeriOpt: Verification-Guided Reinforcement Learning for LLM-Based Compiler Optimization

Xiangxin Fang, Jiaqin Kang, Rodrigo Rocha, Sam Ainsworth 0001, Lev Mukhanov. LLM-VeriOpt: Verification-Guided Reinforcement Learning for LLM-Based Compiler Optimization. In Stephen M. Blackburn, Albert Cohen 0001, Timothy M. Jones 0001, editors, IEEE/ACM International Symposium on Code Generation and Optimization, CGO 2026, Sydney, Australia, January 31 - Feb. 4, 2026. pages 740-755, IEEE, 2026. [doi]

@inproceedings{FangKRAM26,
  title = {LLM-VeriOpt: Verification-Guided Reinforcement Learning for LLM-Based Compiler Optimization},
  author = {Xiangxin Fang and Jiaqin Kang and Rodrigo Rocha and Sam Ainsworth 0001 and Lev Mukhanov},
  year = {2026},
  doi = {10.1109/CGO68049.2026.11395239},
  url = {https://doi.org/10.1109/CGO68049.2026.11395239},
  researchr = {https://researchr.org/publication/FangKRAM26},
  cites = {0},
  citedby = {0},
  pages = {740-755},
  booktitle = {IEEE/ACM International Symposium on Code Generation and Optimization, CGO 2026, Sydney, Australia, January 31 - Feb. 4, 2026},
  editor = {Stephen M. Blackburn and Albert Cohen 0001 and Timothy M. Jones 0001},
  publisher = {IEEE},
  isbn = {979-8-3315-9288-2},
}