# RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot

arXiv: https://arxiv.org/abs/2306.17077 · HTML: https://mlsanity.com/paper/2306.17077/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Unit Test Case Generation with Transformers and Focal Context](https://mlsanity.com/paper/2009.05617/) (2020)
- [Examining Zero-Shot Vulnerability Repair with Large Language Models](https://mlsanity.com/paper/2112.02125/) (2021)
- [Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning](https://mlsanity.com/paper/2207.08281/) (2022)
- [Neural Transfer Learning for Repairing Security Vulnerabilities in C Code](https://mlsanity.com/paper/2104.08308/) (2021)
- [Aroma: Code Recommendation via Structural Code Search](https://mlsanity.com/paper/1812.01158/) (2018)
- [A Comprehensive Study of Automatic Program Repair on the QuixBugs Benchmark](https://mlsanity.com/paper/1805.03454/) (2018)
- [DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons](https://mlsanity.com/paper/2105.09352/) (2021)
- [Learning a Static Analyzer from Data](https://mlsanity.com/paper/1611.01752/) (2016)

## Built on by (most cited first, 14 of 14)

- [A Performance Study of LLM-Generated Code on Leetcode](https://mlsanity.com/paper/2407.21579/) (2024)
- [Search-Based LLMs for Code Optimization](https://mlsanity.com/paper/2408.12159/) (2024)
- [Supersonic: Learning to Generate Source Code Optimizations in C/C++](https://mlsanity.com/paper/2309.14846/) (2023)
- [ZeroLeak: Using LLMs for Scalable and Cost Effective Side-Channel Patching](https://mlsanity.com/paper/2308.13062/) (2023)
- [DCA-Bench: A Benchmark for Dataset Curation Agents](https://mlsanity.com/paper/2406.07275/) (2024)
- [How Do Agents Perform Code Optimization? An Empirical Study](https://mlsanity.com/paper/2512.21757/) (2025)
- [Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language](https://mlsanity.com/paper/2504.19856/) (2025)
- [PerfBench: Can Agents Resolve Real-World Performance Bugs?](https://mlsanity.com/paper/2509.24091/) (2025)
- [Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization](https://mlsanity.com/paper/2603.14703/) (2026)
- [Investigating Execution-Aware Language Models for Code Optimization](https://mlsanity.com/paper/2503.08228/) (2025)
- [Repairing Tool Calls Using Post-tool Execution Reflection and RAG](https://mlsanity.com/paper/2510.17874/) (2025)
- [GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents](https://mlsanity.com/paper/2511.00802/) (2025)
- [Can Coding Agents Implement Missed Compiler Optimizations? Evaluating LLM Agents on LLVM Peephole Optimizations](https://mlsanity.com/paper/2607.02684/) (2026)
- [T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework](https://mlsanity.com/paper/2608.14953/) (2026)

## Abstract (arXiv)

Performance bugs are non-functional bugs that can even manifest in well-tested commercial products. Fixing these performance bugs is an important yet challenging problem. In this work, we address this challenge and present a new approach called Retrieval-Augmented Prompt Generation (RAPGen). Given a code snippet with a performance issue, RAPGen first retrieves a prompt instruction from a pre-constructed knowledge-base of previous performance bug fixes and then generates a prompt using the retrieved instruction. It then uses this prompt on a Large Language Model (such as Codex) in zero-shot to generate a fix. We compare our approach with the various prompt variations and state of the art methods in the task of performance bug fixing. Our evaluation shows that RAPGen can generate performance improvement suggestions equivalent or better than a developer in ~60% of the cases, getting ~42% of them verbatim, in an expert-verified dataset of past performance changes made by C# developers.