# RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment

arXiv: https://arxiv.org/abs/2507.22580 · HTML: https://mlsanity.com/paper/2507.22580/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Randomness In Neural Network Training: Characterizing The Impact of Tooling](https://mlsanity.com/paper/2106.11872/) (2021)
- [A Survey of Learning-based Automated Program Repair](https://mlsanity.com/paper/2301.03270/) (2023)
- [How Often Do Single-Statement Bugs Occur? The ManySStuBs4J Dataset](https://mlsanity.com/paper/1905.13334/) (2019)
- [Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair](https://mlsanity.com/paper/2008.02944/) (2020)
- [Identifying Patch Correctness in Test-Based Program Repair](https://mlsanity.com/paper/1706.09120/) (2017)
- [Automated Patch Assessment for Program Repair at Scale](https://mlsanity.com/paper/1909.13694/) (2019)
- [Empirical Review of Java Program Repair Tools: A Large-Scale Experiment on 2,141 Bugs and 23,551 Repair Attempts](https://mlsanity.com/paper/1905.11973/) (2019)
- [Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning](https://mlsanity.com/paper/2301.01113/) (2023)
- [Automated Classification of Overfitting Patches with Statically Extracted Code Features](https://mlsanity.com/paper/1910.12057/) (2019)
- [Group Relative Policy Optimization for Image Captioning](https://mlsanity.com/paper/2503.01333/) (2025)
- [Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness](https://mlsanity.com/paper/2208.04125/) (2022)
- [APPT: Boosting Automated Patch Correctness Prediction via Fine-tuning Pre-trained Models](https://mlsanity.com/paper/2301.12453/) (2023)
- [Strategic Prompting for Conversational Tasks: A Comparative Analysis of Large Language Models Across Diverse Conversational Tasks](https://mlsanity.com/paper/2411.17204/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)

## Abstract (arXiv)

Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention. However, existing tools tend to generate patches that satisfy test cases without fixing the underlying bug, those are known as overfitting patches. To address this issue, Automated Patch Correctness Assessment (APCA) attempts to identify overfitting patches generated by APR tools. It can be solved as a static approach, meaning that no additional information is needed beyond the original and fixed code snippets. Current static techniques often struggle with reliability, flexibility and transparency. To address these issues, we introduce RePaCA, a novel static APCA technique that leverages Large Language Models (LLMs) specialized in thinking tasks. Our model is prompted with both buggy and fixed code snippets and guided to generate a Chain of Thought that analyses code differences, reasons about how the patch addresses the root cause, and ultimately provides a binary classification: correct or overfitting. To enhance these reasoning capabilities for the APCA task specifically, the LLM is finetuned using Reinforcement Learning with the Group Relative Policy Optimization algorithm. When evaluated on a standard Defects4J-derived test, our approach achieves state-of-the-art performance, with 83.1% accuracy and an 84.8% F1-score. Furthermore, our model demonstrates superior generalization capabilities when trained on different datasets, outperforming the leading technique. This reasoning capability also provides enhanced explainability for the patch assessment. These findings underscore the considerable promise of finetuned, reasoning LLMs to advance static APCA by enhancing accuracy, generalization, and explainability.