# Trust Enhancement Issues in Program Repair

arXiv: https://arxiv.org/abs/2108.13064 · HTML: https://mlsanity.com/paper/2108.13064/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2021.

## Built on by (most cited first, 22 of 22)

- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024)
- [How Effective Are Neural Networks for Fixing Security Vulnerabilities](https://mlsanity.com/paper/2305.18607/) (2023)
- [ITER: Iterative Neural Repair for Multi-Location Patches](https://mlsanity.com/paper/2304.12015/) (2023)
- [Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations](https://mlsanity.com/paper/2407.08983/) (2024)
- [Automated Program Repair: Emerging trends pose and expose problems for benchmarks](https://mlsanity.com/paper/2405.05455/) (2024)
- [The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models](https://mlsanity.com/paper/2505.02931/) (2025)
- [Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback](https://mlsanity.com/paper/2507.18755/) (2025)
- [Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing](https://mlsanity.com/paper/2402.11892/) (2024)
- [Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation](https://mlsanity.com/paper/2410.16655/) (2024)
- [Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair](https://mlsanity.com/paper/2510.03217/) (2025)
- [Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement](https://mlsanity.com/paper/2503.22512/) (2025)
- [Wisdom and Delusion of LLM Ensembles for Code Generation and Repair](https://mlsanity.com/paper/2510.21513/) (2025)
- [EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution](https://mlsanity.com/paper/2605.30105/) (2026)
- [Using ML filters to help automated vulnerability repairs: when it helps and when it doesn't](https://mlsanity.com/paper/2504.07027/) (2025)
- [AutoCodeSherpa: Symbolic Explanations in AI Coding Agents](https://mlsanity.com/paper/2507.22414/) (2025)
- [A Retrospective on ICSE 2022](https://mlsanity.com/paper/2207.12578/) (2022)
- [Mapping the Trust Terrain: LLMs in Software Engineering -- Insights and Perspectives](https://mlsanity.com/paper/2503.13793/) (2025)
- [Knowledge-Enhanced Agentic Vulnerability Repair](https://mlsanity.com/paper/2607.00820/) (2026)
- [Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement](https://mlsanity.com/paper/2607.16692/) (2026)
- [ExplainBench: Evaluating Code Explanations from Agents](https://mlsanity.com/paper/2607.26451/) (2026)

## Abstract (arXiv)

Automated program repair is an emerging technology that seeks to automatically rectify bugs and vulnerabilities using learning, search, and semantic analysis. Trust in automatically generated patches is necessary for achieving greater adoption of program repair. Towards this goal, we survey more than 100 software practitioners to understand the artifacts and setups needed to enhance trust in automatically generated patches. Based on the feedback from the survey on developer preferences, we quantitatively evaluate existing test-suite based program repair tools. We find that they cannot produce high-quality patches within a top-10 ranking and an acceptable time period of 1 hour. The developer feedback from our qualitative study and the observations from our quantitative examination of existing repair tools point to actionable insights to drive program repair research. Specifically, we note that producing repairs within an acceptable time-bound is very much dependent on leveraging an abstract search space representation of a rich enough search space. Moreover, while additional developer inputs are valuable for generating or ranking patches, developers do not seem to be interested in a significant human-in-the-loop interaction.