mlsanityData to 7 Oct 2026

The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers

arXiv 2601.02045 ↗First posted 5 Jan 2026cs.PL cs.AI cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

This survey has provided a systematic overview of the emerging field of LLM-enabled compilation by addressing several key research questions. We first answered how LLMs are being integrated by proposing a comprehensive, multi-dimensional taxonomy that categorizes works based on their Design Philosophy (Selector, Translator, Generator), LLM Methodology, their operational Level of Code Abstraction, and the specific Task Type they address. In answering what advancements these approaches offer, we identified three primary benefits: the democratization of compiler development, the discovery of novel optimization strategies, and the broadening of the compiler's traditional scope. Finally, in addressing the field's challenges and opportunities, we highlighted the critical hurdles of ensuring correctness and achieving scalability, while identifying the development of hybrid systems as the most promising path forward. By providing these answers, this survey serves as a foundational roadmap for researchers and practitioners, charting the course for a new generation of LLM-powered, intelligent, adaptive and synergistic compilation tools.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 94 of its 165 references that are in the map. First posted on arXiv 5 Jan 2026.

Builds on

94 of 165 references.

References · 94

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
  8. 2020Unsupervised Translation of Programming Languagescited by 262
  9. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 246
  10. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  11. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 197
  12. 2023Efficient Guided Generation for Large Language Modelscited by 192
38 more
  1. 2023RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Modelcited by 143
  2. 2022Practical Program Repair in the Era of Large Pre-trained Language Modelscited by 133
  3. 2022Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproductioncited by 110
  4. 2023Learning Performance-Improving Code Editscited by 103
  5. 2021Leveraging Automated Unit Tests for Unsupervised Code Translationcited by 82
  6. 2024XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Modelscited by 73
  7. 2021DOBF: A Deobfuscation Pre-Training Objective for Programming Languagescited by 68
  8. 2025TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operatorscited by 68
  9. 2021AVATAR: A Parallel Corpus for Java-Python Program Translationcited by 59
  10. 2025CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learningcited by 59
  11. 2024OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflectioncited by 56
  12. 2023Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repaircited by 55
  13. 2022NatGen: Generative pre-training by "Naturalizing" source codecited by 53
  14. 2023Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMscited by 45
  15. 2024Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedbackcited by 45
  16. 2022jTrans: Jump-Aware Transformer for Binary Code Similaritycited by 44
  17. 2022Code Translation with Compiler Representationscited by 42
  18. 2024Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTScited by 42
  19. 2021CompilerGym: Robust, Performant Compiler Optimization Environments for AI Researchcited by 41
  20. 2024LLM4Decompile: Decompiling Binary Code with Large Language Modelscited by 38
  21. 2023WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Modelscited by 37
  22. 2024Can Large Language Models Write Parallel Code?cited by 36
  23. 2023SALLM: Security Assessment of Generated Codecited by 35
  24. 2025Type-Constrained Code Generation with Language Modelscited by 32
  25. 2023A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repaircited by 29
  26. 2023SLaDe: A Portable Small Language Model Decompiler for Optimized Assemblycited by 28
  27. 2024EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimizationcited by 28
  28. 2024AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validationcited by 28
  29. 2024Search-Based LLMs for Code Optimizationcited by 27
  30. 2021How could Neural Networks understand Programs?cited by 26
  31. 2024LLM-Vectorizer: LLM-based Verified Loop Vectorizercited by 25
  32. 2024Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Designcited by 24
  33. 2024HLSPilot: LLM-based High-Level Synthesiscited by 24
  34. 2023On the Evaluation of Neural Code Translation: Taxonomy and Benchmarkcited by 23
  35. 2025STARK: Strategic Team of Agents for Refining Kernelscited by 23
  36. 2023HPC-GPT: Integrating Large Language Model for High-Performance Computingcited by 22
  37. 2024PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedbackcited by 22
  38. 2023CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Executioncited by 21

50 most cited of 94 All 94 (JSON)

Built on by

Not cited yet.