{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T10:20:27Z","timestamp":1775038827464,"version":"3.50.1"},"reference-count":163,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2020?62302479?62232015"],"award-info":[{"award-number":["U23B2020?62302479?62232015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BG2024028"],"award-info":[{"award-number":["BG2024028"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2024YFB4505603"],"award-info":[{"award-number":["2024YFB4505603"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s42514-025-00270-x","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:28:38Z","timestamp":1767954518000},"page":"148-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The new compiler stack: a survey on the synergy of LLMs and compilers"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4210-5123","authenticated-orcid":false,"given":"Shuoming","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5228-8972","authenticated-orcid":false,"given":"Jiacheng","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6300-3644","authenticated-orcid":false,"given":"Qiuchu","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2014-5453","authenticated-orcid":false,"given":"Chunwei","family":"Xia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6157-0662","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2909-7750","authenticated-orcid":false,"given":"Xiaobing","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2491-7679","authenticated-orcid":false,"given":"Huimin","family":"Cui","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"270_CR1","unstructured":"Armengol-Estape, J., O\u2019Boyle, M.: Learning c to x86 translation: An experiment in neural compilation. In: Advances in Programming Languages and Neurosymbolic Systems Workshop (2021)"},{"key":"270_CR2","unstructured":"Armengol-Estape, J., Rocha, R.C.O., Woodruff, J., Minervini, P., O\u2019Boyle, M.: Forklift: An extensible neural lifter. In: First Conference on Language Modeling (2024). https:\/\/openreview.net\/forum?id=LWfDcI6txJ"},{"key":"270_CR3","doi-asserted-by":"publisher","unstructured":"Armengol-Estap\u00e9, J., Woodruff, J., Brauckmann, A., Magalh\u00e3es, J.W.d.S., O\u2019Boyle, M.F.P.: Exebench: an ml-scale dataset of executable c functions. In: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming. MAPS 2022, pp. 50\u201359. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3520312.3534867 . https:\/\/doi.org\/10.1145\/3520312.3534867","DOI":"10.1145\/3520312.3534867"},{"key":"270_CR4","doi-asserted-by":"crossref","unstructured":"Armengol-Estape, J., Woodruff, J., Cummins, C., O\u2019Boyle, M.F.: Slade: A portable small language model decompiler for optimized assembly. In: 2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp. 67\u201380 (2024). IEEE","DOI":"10.1109\/CGO57630.2024.10444788"},{"key":"270_CR5","doi-asserted-by":"crossref","unstructured":"Albuquerque, L., Gheyi, R., Ribeiro, M.: Evaluating the capability of llms in identifying compilation errors in configurable systems. arXiv preprint arXiv:2407.19087 (2024)","DOI":"10.5753\/sbes.2024.3560"},{"key":"270_CR6","doi-asserted-by":"publisher","unstructured":"Ahmad, I., Luo, L.: Unsupervised binary code translation with application to code clone detection and vulnerability discovery. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 14581\u201314592. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.971https:\/\/aclanthology.org\/2023.findings-emnlp.971\/","DOI":"10.18653\/v1\/2023.findings-emnlp.971"},{"key":"270_CR7","unstructured":"Lachaux, M.-a., Roziere, B., Szafraniec, M., Lample, G.: DOBF: A deobfuscation pre-training objective for programming languages. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=3ez9BSHTNT"},{"key":"270_CR8","unstructured":"Anthropic: The claude 3 model family: Opus, sonnet, haiku. Technical report, Anthropic (March 2024). Available at https:\/\/www.anthropic.com\/news\/claude-3-family"},{"key":"270_CR9","unstructured":"anthropics: claude-code: a command line interface for Anthropic\u2019s Claude AI. GitHub. Accessed: August 11, 2025 (2025)"},{"key":"270_CR10","unstructured":"Anysphere, Inc.: Cursor: The AI-first Code Editor. https:\/\/cursor.sh\/ (2023). Accessed: 11 Aug 2025"},{"key":"270_CR11","unstructured":"Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., Jiang, E., Cai, C., Terry, M., Le, Q., Sutton, C.: Program Synthesis with Large Language Models (2021). arxiv:2108.07732"},{"key":"270_CR12","doi-asserted-by":"publisher","unstructured":"Ahmad, W.U., Tushar, M.G.R., Chakraborty, S., Chang, K.-W.: AVATAR: A parallel corpus for java-python program translation. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Findings of the Association for Computational Linguistics: ACL 2023, pp. 2268\u20132281. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.143 . https:\/\/aclanthology.org\/2023.findings-acl.143\/","DOI":"10.18653\/v1\/2023.findings-acl.143"},{"key":"270_CR13","doi-asserted-by":"crossref","unstructured":"Brownlee, A.E., Callan, J., Even-Mendoza, K., Geiger, A., Hanna, C., Petke, J., Sarro, F., Sobania, D.: Enhancing genetic improvement mutations using large language models. In: International Symposium on Search Based Software Engineering, pp. 153\u2013159. Springer (2023)","DOI":"10.1007\/978-3-031-48796-5_13"},{"key":"270_CR14","unstructured":"Berabi, B., He, J., Raychev, V., Vechev, M.: Tfix: Learning to fix coding errors with a text-to-text transformer. In: International Conference on Machine Learning, pp. 780\u2013791. PMLR (2021)"},{"key":"270_CR15","unstructured":"Baronio, C., Marsella, P., Pan, B., Guo, S., Alberti, S.: Kevin: Multi-Turn RL for Generating CUDA Kernels (2025). arxiv:2507.11948"},{"key":"270_CR16","doi-asserted-by":"publisher","first-page":"41394","DOI":"10.52202\/079017-1310","volume":"37","author":"S Bhatia","year":"2024","unstructured":"Bhatia, S., Qiu, J., Hasabnis, N., Seshia, S.A., Cheung, A.: Verified code transpilation with llms. Adv. Neural. Inf. Process. Syst. 37, 41394\u201341424 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"270_CR17","doi-asserted-by":"publisher","unstructured":"Bi, Z., Wan, Y., Wang, Z., Zhang, H., Guan, B., Lu, F., Zhang, Z., Sui, Y., Jin, H., Shi, X.: Iterative refinement of project-level code context for precise code generation with compiler feedback. In: Ku, L.-W., Martins, A., Srikumar, V. (eds.) Findings of the Association for Computational Linguistics: ACL 2024, pp. 2336\u20132353. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.138 . https:\/\/aclanthology.org\/2024.findings-acl.138\/","DOI":"10.18653\/v1\/2024.findings-acl.138"},{"key":"270_CR18","doi-asserted-by":"crossref","unstructured":"Chakraborty, S., Ahmed, T., Ding, Y., Devanbu, P.T., Ray, B.: Natgen: generative pre-training by \u201cnaturalizing\u201d source code. In: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 18\u201330 (2022)","DOI":"10.1145\/3540250.3549162"},{"key":"270_CR19","doi-asserted-by":"crossref","unstructured":"Cai, S., Chen, H., Huang, Y., Ming, Z.: Compat: A compiler principles course assistant. In: KSEM (5), pp. 74\u201383 (2024)","DOI":"10.1007\/978-981-97-5489-2_7"},{"key":"270_CR20","doi-asserted-by":"publisher","unstructured":"Cassano, F., Gouwar, J., Lucchetti, F., Schlesinger, C., Freeman, A., Anderson, C.J., Feldman, M.Q., Greenberg, M., Jangda, A., Guha, A.: Knowledge transfer from high-resource to low-resource programming languages for code llms. Proc. ACM Program. Lang. 8(OOPSLA2) (2024) https:\/\/doi.org\/10.1145\/3689735","DOI":"10.1145\/3689735"},{"key":"270_CR21","doi-asserted-by":"crossref","unstructured":"Cao, Y., Liang, R., Chen, K., Hu, P.: Boosting neural networks to decompile optimized binaries. In: Proceedings of the 38th Annual Computer Security Applications Conference, pp. 508\u2013518 (2022)","DOI":"10.1145\/3564625.3567998"},{"key":"270_CR22","unstructured":"Chen, T., Moreau, T., Jiang, Z., Zheng, L., Yan, E., Cowan, M., Shen, H., Wang, L., Hu, Y., Ceze, L., Guestrin, C., Krishnamurthy, A.: Tvm: an automated end-to-end optimizing compiler for deep learning. In: Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation. OSDI\u201918, pp. 579\u2013594. USENIX Association, USA (2018)"},{"key":"270_CR23","unstructured":"Cummins, C., Seeker, V., Armengol-Estap\u00e9, J., Markosyan, A.H., Synnaeve, G., Leather, H.: Don\u2019t Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs (2024). arxiv:2410.08806"},{"key":"270_CR24","unstructured":"Cummins, C., Seeker, V., Grubisic, D., Elhoushi, M., Liang, Y., Roziere, B., Gehring, J., Gloeckle, F., Hazelwood, K., Synnaeve, G., Leather, H.: Large Language Models for Compiler Optimization (2023). arxiv:2309.07062"},{"key":"270_CR25","doi-asserted-by":"publisher","unstructured":"Cummins, C., Seeker, V., Grubisic, D., Roziere, B., Gehring, J., Synnaeve, G., Leather, H.: Llm compiler: Foundation language models for compiler optimization. In: Proceedings of the 34th ACM SIGPLAN International Conference on Compiler Construction. CC \u201925, pp. 141\u2013153. Association for Computing Machinery, New York, NY, USA (2025)https:\/\/doi.org\/10.1145\/3708493.3712691 . https:\/\/doi.org\/10.1145\/3708493.3712691","DOI":"10.1145\/3708493.3712691"},{"key":"270_CR26","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Oliveira\u00a0Pinto, H.P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A., Puri, R., Krueger, G., Petrov, M., Khlaaf, H., Sastry, G., Mishkin, P., Chan, B., Gray, S., Ryder, N., Pavlov, M., Power, A., Kaiser, L., Bavarian, M., Winter, C., Tillet, P., Such, F.P., Cummings, D., Plappert, M., Chantzis, F., Barnes, E., Herbert-Voss, A., Guss, W.H., Nichol, A., Paino, A., Tezak, N., Tang, J., Babuschkin, I., Balaji, S., Jain, S., Saunders, W., Hesse, C., Carr, A.N., Leike, J., Achiam, J., Misra, V., Morikawa, E., Radford, A., Knight, M., Brundage, M., Murati, M., Mayer, K., Welinder, P., McGrew, B., Amodei, D., McCandlish, S., Sutskever, I., Zaremba, W.: Evaluating Large Language Models Trained on Code (2021). arxiv:2107.03374"},{"key":"270_CR27","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.d.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"key":"270_CR28","doi-asserted-by":"crossref","unstructured":"Cummins, C., Wasti, B., Guo, J., Cui, B., Ansel, J., Gomez, S., Jain, S., Liu, J., Teytaud, O., Steiner, B., et al.: Compilergym: Robust, performant compiler optimization environments for ai research. In: 2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp. 92\u2013105. IEEE. (2022)","DOI":"10.1109\/CGO53902.2022.9741258"},{"key":"270_CR29","doi-asserted-by":"publisher","unstructured":"Cui, T., Yew, P.-C., McCamant, S., Zhai, A.: DeCOS: Data-efficient reinforcement learning for compiler optimization selection ignited by LLM. In: Proceedings of the 2025 International Conference on Supercomputing. ICS \u201925. Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3721145.3725765 . https:\/\/doi.org\/10.1145\/3721145.3725765","DOI":"10.1145\/3721145.3725765"},{"key":"270_CR30","doi-asserted-by":"crossref","unstructured":"Cui, F., Yin, C., Zhou, K., Xiao, Y., Sun, G., Xu, Q., Guo, Q., Liang, Y., Zhang, X., Song, D., et al.: Origen: Enhancing rtl code generation with code-to-code augmentation and self-reflection. In: Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design, pp. 1\u20139 (2024)","DOI":"10.1145\/3676536.3676830"},{"key":"270_CR31","unstructured":"Chen, L., Zhang, S., Xu, F., Xing, Z., Wan, L., Zhang, X., Feng, Z.: A test-free semantic mistakes localization framework in neural code translation. arXiv preprint arXiv:2410.22818 (2024)"},{"key":"270_CR32","doi-asserted-by":"publisher","unstructured":"Ding, X., Chen, L., Emani, M., Liao, C., Lin, P.-H., Vanderbruggen, T., Xie, Z., Cerpa, A., Du, W.: Hpc-gpt: Integrating large language model for high-performance computing. In: Proceedings of the SC \u201923 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis. SC-W \u201923, pp. 951\u2013960. Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3624062.3624172 . https:\/\/doi.org\/10.1145\/3624062.3624172","DOI":"10.1145\/3624062.3624172"},{"key":"270_CR33","unstructured":"DeLorenzo, M., Chowdhury, A.B., Gohil, V., Thakur, S., Karri, R., Garg, S., Rajendran, J.: Make every move count: Llm-based high-quality rtl code generation using mcts. arXiv preprint arXiv:2402.03289 (2024)"},{"key":"270_CR34","unstructured":"Duan, S., Kanakaris, N., Xiao, X., Ping, H., Zhou, C., Ahmed, N.K., Ma, G., Capota, M., Willke, T.L., Nazarian, S., Bogdan, P.: PerfRL: A Small Language Model Framework for Efficient Code Optimization (2025). arxiv:2312.05657"},{"key":"270_CR35","doi-asserted-by":"crossref","unstructured":"Deligiannis, P., Lal, A., Mehrotra, N., Poddar, R., Rastogi, A.: Rustassistant: Using llms to fix compilation errors in rust code. In: 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE), pp. 267\u2013279. IEEE Computer Society (2024)","DOI":"10.1109\/ICSE55347.2025.00022"},{"key":"270_CR36","doi-asserted-by":"crossref","unstructured":"De\u00a0Moura, L., Bj\u00f8rner, N.: Z3: An efficient smt solver. In: Proceedings of the Theory and Practice of Software, 14th International Conference on Tools and Algorithms for the Construction and Analysis of Systems. TACAS\u201908\/ETAPS\u201908, pp. 337\u2013340. Springer, Berlin, Heidelberg (2008)","DOI":"10.1007\/978-3-540-78800-3_24"},{"key":"270_CR37","unstructured":"Dong, Y., Ruan, C.F., Cai, Y., Lai, R., Xu, Z., Zhao, Y., Chen, T.: XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models (2024). arxiv:2411.15100"},{"key":"270_CR38","doi-asserted-by":"crossref","unstructured":"Da\u00a0Silva, A.F., Kind, B.C., Souza\u00a0Magalh\u00e3es, J.W., Rocha, J.N., Guimaraes, B.C.F., Pereira, F.M.Q.: Anghabench: A suite with one million compilable c benchmarks for code-size reduction. In: 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp. 378\u2013390. IEEE. (2021)","DOI":"10.1109\/CGO51591.2021.9370322"},{"key":"270_CR39","unstructured":"Dong, S., Wen, Y., Bi, J., Huang, D., Guo, J., Xu, J., Xu, R., Song, X., Hao, Y., Zhou, X., et al.: Qimeng-xpiler: Transcompiling tensor programs for deep learning systems with a neural-symbolic approach. In: 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25) (2025)"},{"key":"270_CR40","unstructured":"Deng, C., Wu, J., Feng, N., Wang, J., Long, M.: Compilerdream: Learning a compiler world model for general code optimization. arXiv preprint arXiv:2404.16077 (2024)"},{"key":"270_CR41","unstructured":"Dong, J., Yang, Y., Liu, T., Wang, Y., Qi, F., Tarokh, V., Rangadurai, K., Yang, S.: STARK: Strategic Team of Agents for Refining Kernels (2025). arxiv:2510.16996"},{"key":"270_CR42","unstructured":"Fang, X., Mukhanov, L.: Towards llm-based optimization compilers. can llms learn how to apply a single peephole optimization? reasoning is all llms need! (2024). arXiv preprint arXiv:2412.12163"},{"key":"270_CR43","first-page":"49044","volume":"36","author":"D Friedman","year":"2023","unstructured":"Friedman, D., Wettig, A., Chen, D.: Learning transformer programs. Adv. Neural. Inf. Process. Syst. 36, 49044\u201349067 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"270_CR44","unstructured":"Gemini Team, Google: Gemini: A family of highly capable multimodal models (2023). arXiv preprint arXiv:2312.11805"},{"key":"270_CR45","doi-asserted-by":"crossref","unstructured":"Gao, S., Gao, C., Gu, W., Lyu, M.R.: Search-based llms for code optimization. In: 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE), pp. 578\u2013590 (2025). IEEE","DOI":"10.1109\/ICSE55347.2025.00021"},{"key":"270_CR46","doi-asserted-by":"publisher","unstructured":"Gao, Y., Liang, L., Li, Y., Li, R., Wang, Y.: Function-level compilation provenance identification with multi-faceted neural feature distillation and fusion. Electronics 13(9) (2024). https:\/\/doi.org\/10.3390\/electronics13091692","DOI":"10.3390\/electronics13091692"},{"key":"270_CR47","doi-asserted-by":"crossref","unstructured":"Guo, Z.C., Moses, W.S.: Enabling transformers to understand low-level programs. In: 2022 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20139 (2022). IEEE","DOI":"10.1109\/HPEC55821.2022.9926313"},{"key":"270_CR48","unstructured":"google-gemini: gemini-cli: A Google Gemini CLI and Python API. GitHub (2025). Accessed: 11 Aug 2025"},{"key":"270_CR49","doi-asserted-by":"crossref","unstructured":"Guthaus, M.R., Ringenberg, J.S., Ernst, D., Austin, T.M., Mudge, T., Brown, R.B.: Mibench: A free, commercially representative embedded benchmark suite. In: Proceedings of the Fourth Annual IEEE International Workshop on Workload Characterization. WWC-4 (Cat. No. 01EX538), pp. 3\u201314 (2001). IEEE","DOI":"10.1109\/WWC.2001.990739"},{"key":"270_CR50","doi-asserted-by":"crossref","unstructured":"Grubisic, D., Seeker, V., Synnaeve, G., Leather, H., Mellor-Crummey, J., Cummins, C.: Priority sampling of large language models for compilers. In: Proceedings of the 4th Workshop on Machine Learning and Systems, pp. 91\u201397 (2024)","DOI":"10.1145\/3642970.3655831"},{"key":"270_CR51","doi-asserted-by":"publisher","unstructured":"Gao, Z., Wang, H., Wang, Y., Zhang, C.: Virtual compiler is all you need for assembly code search. In: Ku, L.-W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3040\u20133051. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.167 . https:\/\/aclanthology.org\/2024.acl-long.167\/","DOI":"10.18653\/v1\/2024.acl-long.167"},{"key":"270_CR52","doi-asserted-by":"crossref","unstructured":"Gao, H., Yang, Y., Sun, M., Wu, J., Zhou, Y., Xu, B.: Clozemaster: Fuzzing rust compiler by harnessing llms for infilling masked real programs. In: 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE), pp. 712\u2013712 (2025). IEEE Computer Society","DOI":"10.1109\/ICSE55347.2025.00175"},{"key":"270_CR53","doi-asserted-by":"crossref","unstructured":"Geng, H., Zhong, M., Zhang, P., Lv, F., Feng, X.: Optango: Multi-central representation learning against innumerable compiler optimization for binary diffing. In: ISSRE, pp. 774\u2013785 (2023). https:\/\/doi.org\/10.1109\/ISSRE59848.2023.00013","DOI":"10.1109\/ISSRE59848.2023.00013"},{"key":"270_CR54","doi-asserted-by":"crossref","unstructured":"Hong, C., Bhatia, S., Cheung, A., Shao, Y.S.: Autocomp: Llm-driven code optimization for tensor accelerators (2025). arXiv preprint arXiv:2505.18574","DOI":"10.1109\/LAD62341.2024.10691748"},{"key":"270_CR55","doi-asserted-by":"crossref","unstructured":"Hu, L., Chen, G., Shang, X., Cheng, S., Wu, B., LiGangyang, L., Zhu, X., Zhang, W., Yu, N.: CompileAgent: Automated real-world repo-level compilation with tool-integrated LLM-based agent system. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2078\u20132091. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/aclanthology.org\/2025.acl-long.103\/","DOI":"10.18653\/v1\/2025.acl-long.103"},{"key":"270_CR56","first-page":"84482","volume":"37","author":"D Huang","year":"2024","unstructured":"Huang, D., Dai, J., Weng, H., Wu, P., Qing, Y., Cui, H., Guo, Z., Zhang, J.: Effilearner: Enhancing efficiency of generated code via self-optimization. Adv. Neural. Inf. Process. Syst. 37, 84482\u201384522 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"270_CR57","doi-asserted-by":"crossref","unstructured":"Heckel, K.: Neuroevolutionary compiler control for code optimization. In: Proceedings of the Companion Conference on Genetic and Evolutionary Computation, pp. 2362\u20132365 (2023)","DOI":"10.1145\/3583133.3596380"},{"issue":"4","key":"270_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1186736.1186737","volume":"34","author":"JL Henning","year":"2006","unstructured":"Henning, J.L.: Spec cpu2006 benchmark descriptions. ACM SIGARCH Comput. Arch. News 34(4), 1\u201317 (2006)","journal-title":"ACM SIGARCH Comput. Arch. News"},{"key":"270_CR59","doi-asserted-by":"crossref","unstructured":"Hu, P., Liang, R., Chen, K.: Degpt: Optimizing decompiler output with llm. In: Proceedings 2024 Network and Distributed System Security Symposium, vol. 267622140 (2024)","DOI":"10.14722\/ndss.2024.24401"},{"key":"270_CR60","unstructured":"Huang, D., Nan, Z., Hu, X., Jin, P., Peng, S., Wen, Y., Zhang, R., Du, Z., Guo, Q., Pu, Y., Chen, Y.: Anpl: towards natural programming with interactive decomposition. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS \u201923. Curran Associates Inc., Red Hook, NY, USA (2023)"},{"key":"270_CR61","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"270_CR62","doi-asserted-by":"crossref","unstructured":"Italiano, D., Cummins, C.: Finding missed code size optimizations in compilers using large language models. In: Proceedings of the 34th ACM SIGPLAN International Conference on Compiler Construction, pp. 81\u201391 (2025)","DOI":"10.1145\/3708493.3712686"},{"key":"270_CR63","unstructured":"Ishida, S., Corrado, G., Fedoseev, G., Yeo, H., Russell, L., Shotton, J., Henriques, J.F., Hu, A.: Langprop: A code optimization framework using large language models applied to driving. In: ICLR 2024 Workshop on Large Language Model (LLM) Agents (2024). https:\/\/openreview.net\/forum?id=JQJJ9PkdYC"},{"key":"270_CR64","doi-asserted-by":"crossref","unstructured":"Ibrahimzada, A.R., Ke, K., Pawagi, M., Abid, M.S., Pan, R., Sinha, S., Jabbarvand, R.: Alphatrans: A neuro-symbolic compositional approach for repository-level code translation and validation. Proceedings of the ACM on Software Engineering 2(FSE), 2454\u20132476 (2025)","DOI":"10.1145\/3729379"},{"key":"270_CR65","doi-asserted-by":"crossref","unstructured":"Just, R., Jalali, D., Ernst, M.D.: Defects4j: A database of existing faults to enable controlled testing studies for java programs. In: Proceedings of the 2014 International Symposium on Software Testing and Analysis, pp. 437\u2013440 (2014)","DOI":"10.1145\/2610384.2628055"},{"key":"270_CR66","doi-asserted-by":"crossref","unstructured":"Jana, P., Jha, P., Ju, H., Kishore, G., Mahajan, A., Ganesh, V.: Cotran: An llm-based code translator using reinforcement learning with feedback from compiler and symbolic execution. In: ECAI (2024)","DOI":"10.3233\/FAIA240968"},{"key":"270_CR67","unstructured":"Jin, X., Larson, J., Yang, W., Lin, Z.: Binary Code Summarization: Benchmarking ChatGPT\/GPT-4 and Other Large Language Models (2023). arxiv:2312.09601"},{"key":"270_CR68","doi-asserted-by":"crossref","unstructured":"Jin, L., Ruan, Z., Mai, H., Shang, J.: Verilocc: End-to-end cross-architecture register allocation via llm. arXiv preprint arXiv:2506.17506 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1538"},{"key":"270_CR69","doi-asserted-by":"crossref","unstructured":"Jiao, M., Yu, T., Li, X., Qiu, G., Gu, X., Shen, B.: On the evaluation of neural code translation: Taxonomy and benchmark. In: Proceedings of the 38th IEEE\/ACM International Conference on Automated Software Engineering, pp. 1529\u20131541 (2023)","DOI":"10.1109\/ASE56229.2023.00114"},{"key":"270_CR70","unstructured":"Jiang, H., Zhu, J., Wan, Y., Fang, B., Zhang, H., Jin, R., Guan, Q.: Can large language models understand intermediate representations in compilers? arXiv preprint arXiv:2502.06854 (2025)"},{"key":"270_CR71","doi-asserted-by":"publisher","unstructured":"Khan, W., Alrabaee, S., Al-kfairy, M., Tang, J., Raymond Choo, K.-K.: Compiler-provenance identification in obfuscated binaries using vision transformers. Forensic Science International: Digital Investigation 49, 301764 (2024) https:\/\/doi.org\/10.1016\/j.fsidi.2024.301764 . DFRWS USA 2024 - Selected Papers from the 24th Annual Digital Forensics Research Conference USA","DOI":"10.1016\/j.fsidi.2024.301764"},{"key":"270_CR72","unstructured":"Kitchenham, B., Charters, S., et al.: Guidelines for performing systematic literature reviews in software engineering (2007)"},{"key":"270_CR73","unstructured":"Kadosh, T., Hasabnis, N., Soundararajan, P., Vo, V.A., Capota, M., Ahmed, N., Pinter, Y., Oren, G.: OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation (2024). arxiv:2409.14771"},{"key":"270_CR74","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)"},{"issue":"4","key":"270_CR75","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3702979","volume":"34","author":"A Kabir","year":"2025","unstructured":"Kabir, A., Wang, S., Tian, Y., Chen, T.-H., Asaduzzaman, M., Zhang, W.: Zs4c: Zero-shot synthesis of compilable code for incomplete code snippets using llms. ACM Trans. Softw. Eng. Methodol. 34(4), 1\u201330 (2025)","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"270_CR76","doi-asserted-by":"crossref","unstructured":"Kang, S., Yoon, J., Yoo, S.: Large language models are few-shot testers: Exploring llm-based general bug reproduction. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp. 2312\u20132323 (2023). IEEE","DOI":"10.1109\/ICSE48619.2023.00194"},{"key":"270_CR77","unstructured":"Lv, J., He, X., Liu, Y., Dai, X., Shen, A., Li, Y., Hao, J., Ding, J., Hu, Y., Yin, S.: Hpctranscompile: An ai compiler generated dataset for high-performance cuda transpilation and llm preliminary exploration (2025). arXiv preprint arXiv:2506.10401"},{"key":"270_CR78","first-page":"37876","volume":"36","author":"D Lindner","year":"2023","unstructured":"Lindner, D., Kram\u00e1r, J., Farquhar, S., Rahtz, M., McGrath, T., Mikulik, V.: Tracr: Compiled transformers as a laboratory for interpretability. Adv. Neural. Inf. Process. Syst. 36, 37876\u201337899 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"270_CR79","doi-asserted-by":"publisher","unstructured":"Li, J., Li, S., Gao, Z., Shi, Q., Li, Y., Wang, Z., Huang, J., WangHaojie, W., Wang, J., Han, X., Liu, Z., Sun, M.: TritonBench: Benchmarking large language model capabilities for generating triton operators. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 23053\u201323066. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.1183 . https:\/\/aclanthology.org\/2025.findings-acl.1183\/","DOI":"10.18653\/v1\/2025.findings-acl.1183"},{"key":"270_CR80","doi-asserted-by":"publisher","unstructured":"Lopes, N.P., Lee, J., Hur, C.-K., Liu, Z., Regehr, J.: Alive2: bounded translation validation for llvm. In: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation. PLDI 2021, pp. 65\u201379. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3453483.3454030 . https:\/\/doi.org\/10.1145\/3453483.3454030","DOI":"10.1145\/3453483.3454030"},{"key":"270_CR81","unstructured":"Luo, T., Lee, H., Johnson, J.: Neural shape compiler: A unified framework for transforming between text, point cloud, and program. Transactions on Machine Learning Research (2023)"},{"key":"270_CR82","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, S., Zhang, Q., Xie, Z.: Rtllm: An open-source benchmark for design rtl generation with large language model. In: 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 722\u2013727 (2024). IEEE","DOI":"10.1109\/ASP-DAC58780.2024.10473904"},{"key":"270_CR83","unstructured":"Lin, H., Maas, M., Roquemore, M., Hasanzadeh, A., Lewis, F., Simonson, Y., Yang, T.-W., Yazdanbakhsh, A., Altinb\u00fcken, D., Papa, F., et al.: Eco: An llm-driven efficient code optimizer for warehouse scale computers (2025). arXiv preprint arXiv:2503.15669"},{"key":"270_CR84","doi-asserted-by":"crossref","unstructured":"Liu, M., Pinckney, N., Khailany, B., Ren, H.: Verilogeval: Evaluating large language models for verilog code generation. In: 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD), pp. 1\u20138 (2023). IEEE","DOI":"10.1109\/ICCAD57390.2023.10323812"},{"key":"270_CR85","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.-t., Rockt\u00e4schel, T., Riedel, S., Kiela, D.: Retrieval-augmented generation for knowledge-intensive nlp tasks. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS \u201920. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"270_CR86","unstructured":"Li, X., Sun, X., Wang, A., Li, J., Chris, S.: Cuda-l1: Improving cuda optimization via contrastive reinforcement learning (2025). arXiv preprint arXiv:2507.14111"},{"key":"270_CR87","unstructured":"Mannarswamy, S., Das, D.: Learning to Combine Instructions in LLVM Compiler (2022). arxiv:2202.12379"},{"key":"270_CR88","doi-asserted-by":"crossref","unstructured":"M\u00fcndler, N., He, J., Wang, H., Sen, K., Song, D., Vechev, M.: Type-constrained code generation with language models. In: Proceedings of the ACM on Programming Languages 9(PLDI), 601\u2013626 (2025)","DOI":"10.1145\/3729274"},{"key":"270_CR89","doi-asserted-by":"crossref","unstructured":"Mammadli, R., Jannesari, A., Wolf, F.: Static neural compiler optimization via deep reinforcement learning. In: 2020 IEEE\/ACM 6th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC) and Workshop on Hierarchical Parallelism for Exascale Computing (HiPar), pp. 1\u201311 (2020). IEEE","DOI":"10.1109\/LLVMHPCHiPar51896.2020.00006"},{"key":"270_CR90","unstructured":"Madaan, A., Shypula, A., Alon, U., Hashemi, M., Ranganathan, P., Yang, Y., Neubig, G., Yazdanbakhsh, A.: Learning performance-improving code edits (2023). arXiv preprint arXiv:2302.07867"},{"key":"270_CR91","doi-asserted-by":"crossref","unstructured":"Macedo, M., Tian, Y., Cogo, F., Adams, B.: Exploring the impact of the output format on the evaluation of large language models for code translation. In: Proceedings of the 2024 IEEE\/ACM First International Conference on AI Foundation Models and Software Engineering, pp. 57\u201368 (2024)","DOI":"10.1145\/3650105.3652301"},{"key":"270_CR92","doi-asserted-by":"crossref","unstructured":"Nichols, D., Davis, J.H., Xie, Z., Rajaram, A., Bhatele, A.: Can large language models write parallel code? In: Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing, pp. 281\u2013294 (2024)","DOI":"10.1145\/3625549.3658689"},{"key":"270_CR93","doi-asserted-by":"publisher","unstructured":"Niu, C., Li, C., Ng, V., Lo, D., Luo, B.: Fair: Flow type-aware pre-training of compiler intermediate representations. In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. ICSE \u201924. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3597503.3608136 . https:\/\/doi.org\/10.1145\/3597503.3608136","DOI":"10.1145\/3597503.3608136"},{"key":"270_CR94","unstructured":"NVIDIA Corporation: CUTLASS Python Interface Overview. https:\/\/docs.nvidia.com\/cutlass\/media\/docs\/pythonDSL\/overview.html. Accessed: 11 Aug 2025 (2025)"},{"key":"270_CR95","doi-asserted-by":"crossref","unstructured":"Nakkab, A., Zhang, S.Q., Karri, R., Garg, S.: Rome was not built in a single step: Hierarchical prompting for llm-based chip design. In: Proceedings of the 2024 ACM\/IEEE International Symposium on Machine Learning for CAD, pp. 1\u201311 (2024)","DOI":"10.1145\/3670474.3685964"},{"key":"270_CR96","unstructured":"Ouyang, A., Guo, S., Arora, S., Zhang, A.L., Hu, W., Re, C., Mirhoseini, A.: Kernelbench: Can LLMs write efficient GPU kernels? In: Forty-second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=yeoN1iQT1x"},{"key":"270_CR97","doi-asserted-by":"crossref","unstructured":"Ou, X., Li, C., Jiang, Y., Xu, C.: The mutators reloaded: Fuzzing compilers with large language model generated mutation operators. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4, pp. 298\u2013312 (2024)","DOI":"10.1145\/3622781.3674171"},{"key":"270_CR98","unstructured":"OpenAI: GPT-4 Technical Report (2024). arxiv:2303.08774"},{"key":"270_CR99","doi-asserted-by":"crossref","unstructured":"Palkowski, M., Gruzewski, M.: Automatic generation of opencl code through polyhedral compilation with llm. In: 2024 19th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 671\u2013676 (2024). IEEE","DOI":"10.15439\/2024F6469"},{"key":"270_CR100","doi-asserted-by":"crossref","unstructured":"Peng, Y., Gotmare, A.D., Lyu, M.R., Xiong, C., Savarese, S., Sahoo, D.: Perfcodegen: Improving performance of llm generated code with execution feedback. In: 2025 IEEE\/ACM Second International Conference on AI Foundation Models and Software Engineering (Forge), pp. 1\u201313 (2025). IEEE","DOI":"10.1109\/Forge66646.2025.00008"},{"key":"270_CR101","doi-asserted-by":"crossref","unstructured":"Pan, R., Ibrahimzada, A.R., Krishna, R., Sankar, D., Wassi, L.P., Merler, M., Sobolev, B., Pavuluri, R., Sinha, S., Jabbarvand, R.: Lost in translation: A study of bugs introduced by large language models while translating code. In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering, pp. 1\u201313 (2024)","DOI":"10.1145\/3597503.3639226"},{"key":"270_CR102","unstructured":"Puri, R., Kung, D.S., Janssen, G., Zhang, W., Domeniconi, G., Zolotov, V., Dolby, J., Chen, J., Choudhury, M., Decker, L., Thost, V., Buratti, L., Pujar, S., Ramji, S., Finkler, U., Malaika, S., Reiss, F.: CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks (2021). arxiv:2105.12655"},{"key":"270_CR103","doi-asserted-by":"crossref","unstructured":"Purschke, N., Kirchner, S., Knoll, A.: Speedgen: Enhancing code efficiency through large language model-based performance optimization. In: 2025 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 1\u201312 (2025). IEEE","DOI":"10.1109\/SANER64311.2025.00045"},{"key":"270_CR104","doi-asserted-by":"crossref","unstructured":"Pirkelbauer, P., Liao, C.: Compilergpt: Leveraging large language models for analyzing and acting on compiler optimization reports (2025). arXiv preprint arXiv:2506.06227","DOI":"10.1007\/978-3-032-07612-0_25"},{"key":"270_CR105","unstructured":"Pan, H., Lin, H., Luo, H., Liu, Y., Yao, K., Zhang, L., Xing, M., Wu, Y.: Compiler-r1: Towards agentic compiler auto-tuning with reinforcement learning (2025). arXiv preprint arXiv:2506.15701"},{"key":"270_CR106","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"270_CR107","unstructured":"Peng, D., Zheng, S., Li, Y., Ke, G., He, D., Liu, T.-Y.: How could neural networks understand programs? In: International Conference on Machine Learning, pp. 8476\u20138486 (2021). PMLR"},{"issue":"5","key":"270_CR108","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s44443-025-00074-7","volume":"37","author":"Y Rong","year":"2025","unstructured":"Rong, Y., Du, T., Li, R., Bao, W.: Integrating llm-based code optimization with human-like exclusionary reasoning for computational education. J. King Saud Univ. Comput. Inf. Sci. 37(5), 87 (2025)","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"270_CR109","unstructured":"Ren, S., Guo, D., Lu, S., Zhou, L., Liu, S., Tang, D., Sundaresan, N., Zhou, M., Blanco, A., Ma, S.: Codebleu: a method for automatic evaluation of code synthesis (2020). arXiv preprint arXiv:2009.10297"},{"key":"270_CR110","unstructured":"Roziere, B., Lachaux, M.-A., Chanussot, L., Lample, G.: Unsupervised translation of programming languages. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS \u201920. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"270_CR111","doi-asserted-by":"crossref","unstructured":"Romero\u00a0Rosas, M.A., Torres\u00a0Sanchez, M.A., Eigenmann, R.: Should ai optimize your code? a comparative study of classical optimizing compilers versus current large language models. In: Proceedings of the 2025 Supercomputing Asia Conference, pp. 22\u201329 (2025)","DOI":"10.1145\/3718350.3718357"},{"key":"270_CR112","unstructured":"Roziere, B., Zhang, J., Charton, F., Harman, M., Synnaeve, G., Lample, G.: Leveraging automated unit tests for unsupervised code translation. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=cmt-6KtR4c4"},{"key":"270_CR113","doi-asserted-by":"crossref","unstructured":"Ren, X., Zhang, T., Xu, X., Zheng, Y.-C., Zhang, S.: Leveraging machine learning for quantum compilation optimization. In: Proceedings of the 61st ACM\/IEEE Design Automation Conference, pp. 1\u20134 (2024)","DOI":"10.1145\/3649329.3663510"},{"key":"270_CR114","doi-asserted-by":"crossref","unstructured":"Sajjadinasab, R., Arora, S., Drepper, U., Sanaullah, A., Herbordt, M.: A graph-based algorithm for optimizing gcc compiler flag settings. In: 2024 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20138 (2024). IEEE","DOI":"10.1109\/HPEC62836.2024.10938458"},{"key":"270_CR115","unstructured":"Shaw, P., Cohan, J., Eisenstein, J., Lee, K., Berant, J., Toutanova, K.: ALTA: Compiler-based analysis of transformers. Trans. Mach. Learn. Res. (2025)"},{"key":"270_CR116","doi-asserted-by":"publisher","unstructured":"Sun, T., Chai, L., Yang, J., Yin, Y., Guo, H., Liu, J., Wang, B., Yang, L., Li, Z.: UniCoder: Scaling code large language model via universal code. In: Ku, L.-W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1812\u20131824. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.100 . https:\/\/aclanthology.org\/2024.acl-long.100\/","DOI":"10.18653\/v1\/2024.acl-long.100"},{"key":"270_CR117","doi-asserted-by":"publisher","unstructured":"Siddiq, M.L., Silva\u00a0Santos, J.C., Devareddy, S., Muller, A.: Sallm: Security assessment of generated code. In: Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering Workshops. ASEW \u201924, pp. 54\u201365. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3691621.3694934 . https:\/\/doi.org\/10.1145\/3691621.3694934","DOI":"10.1145\/3691621.3694934"},{"key":"270_CR118","unstructured":"Saldyt, L., Kambhampati, S.: Algorithmic Language Models with Neurally Compiled Libraries (2025). arxiv:2407.04899"},{"key":"270_CR119","doi-asserted-by":"crossref","unstructured":"Sibaee, S., Najar, O., Ghouti, L., Koubaa, A.: Llms as compiler for arabic programming language (2024). arXiv preprint arXiv:2403.16087","DOI":"10.1007\/978-3-031-90573-5_8"},{"key":"270_CR120","unstructured":"Szafraniec, M., Roziere, B., Leather, H.J., Labatut, P., Charton, F., Synnaeve, G.: Code translation with compiler representations. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=XomEU3eNeSQ"},{"key":"270_CR121","unstructured":"Shao, Z., Wang, P., Zhu, Q., Xu, R., Song, J., Bi, X., Zhang, H., Zhang, M., Li, Y.K., Wu, Y., Guo, D.: DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models (2024). arxiv:2402.03300"},{"key":"270_CR122","doi-asserted-by":"crossref","unstructured":"Shen, L., Yang, Q., Zheng, Y., Li, M.: Autoiot: Llm-driven automated natural language programming for aiot applications. In: Mobicom 2025 (2025)","DOI":"10.1145\/3680207.3723486"},{"key":"270_CR123","unstructured":"Tabnine: Tabnine: AI Code Completion Tool. https:\/\/www.tabnine.com\/. Accessed: 11 Aug 2025 (2022)"},{"key":"270_CR124","doi-asserted-by":"publisher","unstructured":"Thakur, S., Ahmad, B., Pearce, H., Tan, B., Dolan-Gavitt, B., Karri, R., Garg, S.: Verigen: A large language model for verilog code generation. ACM Trans. Des. Autom. Electron. Syst. 29(3) (2024) https:\/\/doi.org\/10.1145\/3643681","DOI":"10.1145\/3643681"},{"key":"270_CR125","unstructured":"TehraniJamsaz, A., Bhattacharjee, A., Chen, L., Ahmed, N.K., Yazdanbakhsh, A., Jannesari, A.: Coderosetta: Pushing the boundaries of unsupervised code translation for parallel programming. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024). https:\/\/openreview.net\/forum?id=V6hrg4O9gg"},{"key":"270_CR126","unstructured":"Thakur, S., Blocklove, J., Pearce, H., Tan, B., Garg, S., Karri, R.: Autochip: Automating hdl generation using llm feedback (2023). arXiv preprint arXiv:2311.04887"},{"key":"270_CR127","unstructured":"Tavarageri, S., Goyal, G., Avancha, S., Kaul, B., Upadrasta, R.: Ai powered compiler techniques for dl code optimization (2021). arXiv preprint arXiv:2104.05573"},{"key":"270_CR128","doi-asserted-by":"publisher","unstructured":"Tillet, P., Kung, H.T., Cox, D.: Triton: an intermediate language and compiler for tiled neural network computations. In: Proceedings of the 3rd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages. MAPL 2019, pp. 10\u201319. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3315508.3329973 . https:\/\/doi.org\/10.1145\/3315508.3329973","DOI":"10.1145\/3315508.3329973"},{"key":"270_CR129","doi-asserted-by":"publisher","unstructured":"Tan, H., Luo, Q., Li, J., Zhang, Y.: LLM4Decompile: Decompiling binary code with large language models. In: Al-Onaizan, Y., Bansal, M., Chen, Y.-N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 3473\u20133487. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.203 . https:\/\/aclanthology.org\/2024.emnlp-main.203\/","DOI":"10.18653\/v1\/2024.emnlp-main.203"},{"key":"270_CR130","doi-asserted-by":"publisher","unstructured":"Taneja, J., Laird, A., Yan, C., Musuvathi, M., Lahiri, S.K.: Llm-vectorizer: Llm-based verified loop vectorizer. In: Proceedings of the 23rd ACM\/IEEE International Symposium on Code Generation and Optimization. CGO \u201925, pp. 137\u2013149. Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3696443.3708929 . https:\/\/doi.org\/10.1145\/3696443.3708929","DOI":"10.1145\/3696443.3708929"},{"key":"270_CR131","unstructured":"Tang, S., Priebe, C., Mahapatra, R., Qin, L., Esmaeilzadeh, H.: Compiler optimization via llm reasoning for efficient model serving (2025). arXiv preprint arXiv:2506.01374"},{"key":"270_CR132","unstructured":"Tsimpourlas, F., Petoumenos, P., Xu, M., Cummins, C., Hazelwood, K., Rajan, A., Leather, H.: BenchDirect: A Directed Language Model for Compiler Benchmarks (2023). arxiv:2303.01557"},{"key":"270_CR133","doi-asserted-by":"publisher","unstructured":"Taylor, A., Vassar, A., Renzella, J., Pearce, H.: dcc \u2013help: Transforming the role of the compiler by generating context-aware error explanations with large language models. In: Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1. SIGCSE 2024, pp. 1314\u20131320. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3626252.3630822 . https:\/\/doi.org\/10.1145\/3626252.3630822","DOI":"10.1145\/3626252.3630822"},{"key":"270_CR134","unstructured":"Wen, Y., Guo, Q., Fu, Q., Li, X., Xu, J., Tang, Y., Zhao, Y., Hu, X., Du, Z., Li, L., et al.: Babeltower: Learning to auto-parallelized program translation. In: International Conference on Machine Learning, pp. 23685\u201323700 (2022). PMLR"},{"key":"270_CR135","unstructured":"Weiss, G., Goldberg, Y., Yahav, E.: Thinking like transformers. In: International Conference on Machine Learning, pp. 11080\u201311090 (2021). PMLR"},{"key":"270_CR136","doi-asserted-by":"publisher","unstructured":"Wang, X., Hui, X., Liao, C., Shen, X.: Reductive analysis with compiler-guided large language models for input-centric code optimizations. Proc. ACM Program. Lang. 9(PLDI) (2025) https:\/\/doi.org\/10.1145\/3729282","DOI":"10.1145\/3729282"},{"key":"270_CR137","unstructured":"Willard, B.T., Louf, R.: Efficient Guided Generation for Large Language Models (2023). arxiv:2307.09702"},{"issue":"11","key":"270_CR138","doi-asserted-by":"publisher","first-page":"1879","DOI":"10.1109\/JPROC.2018.2817118","volume":"106","author":"Z Wang","year":"2018","unstructured":"Wang, Z., O\u2019Boyle, M.: Machine learning in compiler optimization. Proc. IEEE 106(11), 1879\u20131901 (2018). https:\/\/doi.org\/10.1109\/JPROC.2018.2817118","journal-title":"Proc. IEEE"},{"key":"270_CR139","doi-asserted-by":"publisher","unstructured":"Wang, H., Qu, W., Katz, G., Zhu, W., Gao, Z., Qiu, H., Zhuge, J., Zhang, C.: jtrans: jump-aware transformer for binary code similarity detection. In: Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2022, pp. 1\u201313. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3533767.3534367 . https:\/\/doi.org\/10.1145\/3533767.3534367","DOI":"10.1145\/3533767.3534367"},{"key":"270_CR140","doi-asserted-by":"crossref","unstructured":"Wang, T., Wang, R., Chen, Y., Yu, L., Pan, Z., Zhang, M., Ma, H., Zheng, J.: Enhancing black-box compiler option fuzzing with llm through command feedback. In: 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE), pp. 319\u2013330. IEEE. (2024)","DOI":"10.1109\/ISSRE62328.2024.00039"},{"key":"270_CR141","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E.H., Le, Q.V., Zhou, D.: Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. NIPS \u201922. Curran Associates Inc., Red Hook, NY, USA (2022)"},{"key":"270_CR142","doi-asserted-by":"crossref","unstructured":"Wong, W.K., Wu, D., Wang, H., Li, Z., Liu, Z., Wang, S., Tang, Q., Nie, S., Wu, S.: Decllm: Llm-augmented recompilable decompilation for enabling programmatic use of decompiled code. Proceedings of the ACM on Software Engineering 2(ISSTA), 1841\u20131864 (2025)","DOI":"10.1145\/3728958"},{"key":"270_CR143","doi-asserted-by":"publisher","unstructured":"Wei, Y., Xia, C.S., Zhang, L.: Copiloting the copilots: Fusing large language models with completion engines for automated program repair. In: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2023, pp. 172\u2013184. Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3611643.3616271 . https:\/\/doi.org\/10.1145\/3611643.3616271","DOI":"10.1145\/3611643.3616271"},{"key":"270_CR144","unstructured":"Wang, Y., Ye, W., Guo, P., He, Y., Wang, Z., Tian, B., He, S., Sun, G., Shen, Z., Chen, S., et al.: Symrtlo: Enhancing rtl code optimization with llms and neuron-inspired symbolic reasoning (2025). arXiv preprint arXiv:2504.10369"},{"key":"270_CR145","unstructured":"Wang, N., Yao, B., Zhou, J., Hu, Y., Wang, X., Guan, N., Jiang, Z.: Insights from verification: Training a verilog generation llm with reinforcement learning with testbench feedback (2025). arXiv preprint arXiv:2504.15804"},{"key":"270_CR146","doi-asserted-by":"publisher","unstructured":"Xu, X., Feng, S., Ye, Y., Shen, G., Su, Z., Cheng, S., Tao, G., Shi, Q., Zhang, Z., Zhang, X.: Improving binary code similarity transformer models by semantics-driven instruction deemphasis. In: Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2023, pp. 1106\u20131118. Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3597926.3598121 . https:\/\/doi.org\/10.1145\/3597926.3598121","DOI":"10.1145\/3597926.3598121"},{"issue":"8","key":"270_CR147","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1007\/s11227-025-07378-5","volume":"81","author":"C Xu","year":"2025","unstructured":"Xu, C., Guo, H., Cen, C., Chen, M., Tao, X., He, J.: Efficient program optimization through knowledge-enhanced lora fine-tuning of large language models. J. Supercomput. 81(8), 1006 (2025)","journal-title":"J. Supercomput."},{"key":"270_CR148","doi-asserted-by":"crossref","unstructured":"Xiong, C., Liu, C., Li, H., Li, X.: Hlspilot: Llm-based high-level synthesis. In: Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design, pp. 1\u20139 (2024)","DOI":"10.1145\/3676536.3676781"},{"key":"270_CR149","unstructured":"Xu, S., Li, Z., Mei, K., Zhang, Y.: Aios compiler: Llm as interpreter for natural language programming and flow programming of ai agents. arXiv preprint arXiv:2405.06907 (2024)"},{"key":"270_CR150","doi-asserted-by":"publisher","unstructured":"Xia, C.S., Wei, Y., Zhang, L.: Automated program repair in the era of large pre-trained language models. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp. 1482\u20131494 (2023). https:\/\/doi.org\/10.1109\/ICSE48619.2023.00129","DOI":"10.1109\/ICSE48619.2023.00129"},{"key":"270_CR151","doi-asserted-by":"crossref","unstructured":"Xu, Q., Yang, D., Zhang, L.: Code optimization chain-of-thought: Structured understanding and self-checking. In: Proceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms, pp. 425\u2013430 (2024)","DOI":"10.1145\/3690407.3690479"},{"key":"270_CR152","unstructured":"Xu, X., Zhang, Z., Feng, S., Ye, Y., Su, Z., Jiang, N., Cheng, S., Tan, L., Zhang, X.: Lmpa: Improving decompilation by synergy of large language model and program analysis (2023). arXiv preprint arXiv:2306.02546"},{"issue":"OOPSLA2","key":"270_CR153","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1145\/3689736","volume":"8","author":"C Yang","year":"2024","unstructured":"Yang, C., Deng, Y., Lu, R., Yao, J., Liu, J., Jabbarvand, R., Zhang, L.: Whitefox: White-box compiler fuzzing empowered by large language models. Proc. ACM Program. Lang. 8(OOPSLA2), 709\u2013735 (2024)","journal-title":"Proc. ACM Program. Lang."},{"key":"270_CR154","unstructured":"Ye, T., Ma, T., Zhang, X., Yu, H., Yin, J., Wang, W.: A problem-oriented perspective and anchor verification for code optimization (2024). arXiv preprint arXiv:2406.11935"},{"key":"270_CR155","doi-asserted-by":"crossref","unstructured":"Yin, X., Ni, C., Nguyen, T.N., Wang, S., Yang, X.: Rectifier: Code translation with corrector via llms (2024). arXiv preprint arXiv:2407.07472","DOI":"10.2139\/ssrn.5165318"},{"key":"270_CR156","doi-asserted-by":"crossref","unstructured":"Zhang, H., David, C., Wang, M., Paulsen, B., Kroening, D.: Scalable, validated code translation of entire projects using large language models. Proceedings of the ACM on Programming Languages 9(PLDI), 1616\u20131641 (2025)","DOI":"10.1145\/3729315"},{"key":"270_CR157","unstructured":"Zhong, M., LYU, F., Wang, L., Geng, H., Qiu, L., Cui, H., Feng, X.: Comback: A versatile dataset for enhancing compiler backend development efficiency. In: The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2024). https:\/\/openreview.net\/forum?id=vfju5hjrJw"},{"key":"270_CR158","doi-asserted-by":"publisher","unstructured":"Zhong, M., Lv, F., Wang, L., Qiu, L., Wang, Y., Liu, Y., Cui, H., Feng, X., Xue, J.: Vega: Automatically generating compiler backends using a pre-trained transformer model. In: Proceedings of the 23rd ACM\/IEEE International Symposium on Code Generation and Optimization. CGO \u201925, pp. 90\u2013106. Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3696443.3708931 . https:\/\/doi.org\/10.1145\/3696443.3708931","DOI":"10.1145\/3696443.3708931"},{"key":"270_CR159","unstructured":"Zhang, Y., Song, W., Ji, Z., Danfeng, Yao, Meng, N.: How well does LLM generate security tests? (2023). arxiv:2310.00710"},{"key":"270_CR160","unstructured":"Zhai, Y., Yang, S., Pan, K., Zhang, R., Liu, S., Liu, C., Ye, Z., Ji, J., Zhao, J., Zhang, Y., et al.: Enabling tensor language model to assist in generating $$\\{$$High-Performance$$\\}$$ tensor programs for deep learning. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 289\u2013305 (2024)"},{"key":"270_CR161","doi-asserted-by":"publisher","unstructured":"Zhang, S., Zhao, J., Xia, C., Wang, Z., Chen, Y., Cui, H.: Introducing compiler semantics into large language models as programming language translators: A case study of C to x86 assembly. In: Al-Onaizan, Y., Bansal, M., Chen, Y.-N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 996\u20131011. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.55 . https:\/\/aclanthology.org\/2024.findings-emnlp.55\/","DOI":"10.18653\/v1\/2024.findings-emnlp.55"},{"key":"270_CR162","unstructured":"Zhang, S., Zhao, J., Xia, C., Wang, Z., Chen, Y., Feng, X., Cui, H.: LEGO-Compiler: Enhancing Neural Compilation Through Translation Composability (2025). arxiv:2505.20356"},{"key":"270_CR163","unstructured":"Zhang, Q., Zhang, T., Zhai, J., Fang, C., Yu, B., Sun, W., Chen, Z.: A critical review of large language model on software engineering: An example from chatgpt and automated program repair. arXiv preprint arXiv:2310.08879 (2023)"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00270-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-025-00270-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00270-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:09:38Z","timestamp":1775030978000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-025-00270-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":163,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["270"],"URL":"https:\/\/doi.org\/10.1007\/s42514-025-00270-x","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]},"assertion":[{"value":"29 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}