mlsanityData to 7 Oct 2026

Compiler generated feedback for Large Language Models

arXiv 2403.14714 ↗First posted 18 Mar 2024cs.PL cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly. The model takes unoptimized LLVM IR as input and produces optimized IR, the best optimization passes, and instruction counts of both unoptimized and optimized IRs. Then we compile the input with generated optimization passes and evaluate if the predicted instruction count is correct, generated IR is compilable, and corresponds to compiled code. We provide this feedback back to LLM and give it another chance to optimize code. This approach adds an extra 0.53% improvement over -Oz to the original model. Even though, adding more information with feedback seems intuitive, simple sampling techniques achieve much higher performance given 10 or more samples.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

21 of 39 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  7. 2023Large Language Models as Optimizerscited by 830
  8. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 492
  9. 2020Unsupervised Translation of Programming Languagescited by 262
  10. 2022Practical Program Repair in the Era of Large Pre-trained Language Modelscited by 133
  11. 2022Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Modelscited by 102
  12. 2023Large Language Models for Compiler Optimizationcited by 52
9 more
  1. 2022Code Translation with Compiler Representationscited by 42
  2. 2021MLGO: a Machine Learning Guided Compiler Optimizations Frameworkcited by 40
  3. 2019NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learningcited by 37
  4. 2020AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learningcited by 24
  5. 2023Fixing Hardware Security Bugs with Large Language Modelscited by 24
  6. 2018Machine Learning in Compiler Optimisationcited by 13
  7. 2021Automated Conformance Testing for JavaScript Engines via Deep Compiler Fuzzingcited by 12
  8. 2023Learning Compiler Pass Orders using Coreset and Normalized Value Predictioncited by 11
  9. 2022MLGOPerf: An ML Guided Inliner to Optimize Performancecited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2024Meta Large Language Model Compiler: Foundation Models of Compiler Optimizationcited by 39
  2. 2024Towards a Unified View of Preference Learning for Large Language Models: A Surveycited by 17
  3. 2025SuperCoder: Assembly Program Superoptimization with Large Language Modelscited by 5
  4. 2025Prompt to Pwn: Automated Exploit Generation for Smart Contractscited by 4
  5. 2025Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop Optimizationcited by 4
  6. 2025Towards Secure Program Partitioning for Smart Contracts with LLM's In-Context Learningcited by 2
  7. 2025LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Modelscited by 1
  8. 2026From LLMs to Agents in Programming: The Impact of Providing an LLM with a Compilercited by 1
  9. 2026Natural-Language to SysMLv2 Translation via Conformance-Driven Iterative Refinementcited by 0