# Enhancing Automated Program Repair with Solution Design

arXiv: https://arxiv.org/abs/2408.12056 · HTML: https://mlsanity.com/paper/2408.12056/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 72 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Builds on (most cited first, 30 of 30)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [Impact of Code Language Models on Automated Program Repair](https://mlsanity.com/paper/2302.05020/) (2023)
- [Towards Mitigating Hallucination in Large Language Models via Self-Reflection](https://mlsanity.com/paper/2310.06271/) (2023)
- [TBar: Revisiting Template-based Automated Program Repair](https://mlsanity.com/paper/1903.08409/) (2019)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [A Deep Dive into Large Language Models for Automated Bug Localization and Repair](https://mlsanity.com/paper/2404.11595/) (2024)
- [Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs](https://mlsanity.com/paper/1811.04211/) (2018)
- [Learning Natural Coding Conventions](https://mlsanity.com/paper/1402.4182/) (2014)
- [On the Efficiency of Test Suite based Program Repair: A Systematic Assessment of 16 Automated Repair Systems for Java Programs](https://mlsanity.com/paper/2008.00914/) (2020)
- [Dissection of a Bug Dataset: Anatomy of 395 Patches from Defects4J](https://mlsanity.com/paper/1801.06393/) (2018)
- [A Survey on Automated Program Repair Techniques](https://mlsanity.com/paper/2303.18184/) (2023)
- [iFixR: Bug Report driven Program Repair](https://mlsanity.com/paper/1907.05620/) (2019)
- [Analysis and Detection of Information Types of Open Source Software Issue Discussions](https://mlsanity.com/paper/1902.07093/) (2019)
- [Learning to Describe Solutions for Bug Reports Based on Developer Discussions](https://mlsanity.com/paper/2110.04353/) (2021)
- [ISPY: Automatic Issue-Solution Pair Extraction from Community Live Chats](https://mlsanity.com/paper/2109.07055/) (2021)
- [Using Developer Discussions to Guide Fixing Bugs in Software](https://mlsanity.com/paper/2211.06335/) (2022)
- [Argument Mining using BERT and Self-Attention based Embeddings](https://mlsanity.com/paper/2302.13906/) (2023)
- [Rationale in Development Chat Messages: An Exploratory Study](https://mlsanity.com/paper/1704.08500/) (2017)
- [Extracting Rationale for Open Source Software Development Decisions -- A Study of Python Email Archives](https://mlsanity.com/paper/2102.05232/) (2021)
- [A First Look at Developers' Live Chat on Gitter](https://mlsanity.com/paper/2107.05823/) (2021)
- [Recommending Bug-fixing Comments from Issue Tracking Discussions in Support of Bug Repair](https://mlsanity.com/paper/2105.11525/) (2021)
- [A Novel Approach for Automated Design Information Mining from Issue Logs](https://mlsanity.com/paper/2405.19623/) (2024)

## Built on by (most cited first, 8 of 8)

- [Issue Localization via LLM-Driven Iterative Code Graph Searching](https://mlsanity.com/paper/2503.22424/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench](https://mlsanity.com/paper/2507.02976/) (2025)
- [SVRepair: Structured Visual Reasoning for Automated Program Repair](https://mlsanity.com/paper/2602.06090/) (2026)
- [FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair](https://mlsanity.com/paper/2603.17826/) (2026)
- [Automated detection of atomicity violations in large-scale systems](https://mlsanity.com/paper/2504.00521/) (2025)
- [Collaborative Agents for Automated Program Repair in Ruby](https://mlsanity.com/paper/2511.03925/) (2025)
- [Improving MPI Error Detection and Repair with Large Language Models and Bug References](https://mlsanity.com/paper/2604.02398/) (2026)

## Abstract (arXiv)

Automatic Program Repair (APR) endeavors to autonomously rectify issues within specific projects, which generally encompasses three categories of tasks: bug resolution, new feature development, and feature enhancement. Despite extensive research proposing various methodologies, their efficacy in addressing real issues remains unsatisfactory. It's worth noting that, typically, engineers have design rationales (DR) on solution-planed solutions and a set of underlying reasons-before they start patching code. In open-source projects, these DRs are frequently captured in issue logs through project management tools like Jira. This raises a compelling question: How can we leverage DR scattered across the issue logs to efficiently enhance APR? To investigate this premise, we introduce DRCodePilot, an approach designed to augment GPT-4-Turbo's APR capabilities by incorporating DR into the prompt instruction. Furthermore, given GPT-4's constraints in fully grasping the broader project context and occasional shortcomings in generating precise identifiers, we have devised a feedback-based self-reflective framework, in which we prompt GPT-4 to reconsider and refine its outputs by referencing a provided patch and suggested identifiers. We have established a benchmark comprising 938 issue-patch pairs sourced from two open-source repositories hosted on GitHub and Jira. Our experimental results are impressive: DRCodePilot achieves a full-match ratio that is a remarkable 4.7x higher than when GPT-4 is utilized directly. Additionally, the CodeBLEU scores also exhibit promising enhancements. Moreover, our findings reveal that the standalone application of DR can yield promising increase in the full-match ratio across CodeLlama, GPT-3.5, and GPT-4 within our benchmark suite. We believe that our DRCodePilot initiative heralds a novel human-in-the-loop avenue for advancing the field of APR.