# A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications

arXiv: https://arxiv.org/abs/2506.23749 · HTML: https://mlsanity.com/paper/2506.23749/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2025.

## Built on by (most cited first, 25 of 25)

- [SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints](https://mlsanity.com/paper/2509.09853/) (2025)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents](https://mlsanity.com/paper/2510.20211/) (2025)
- [SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution](https://mlsanity.com/paper/2603.01327/) (2026)
- [EviACT: An Evidence-to-Action Framework for Agentic Program Repair](https://mlsanity.com/paper/2605.27238/) (2026)
- [How Robustly do LLMs Understand Execution Semantics?](https://mlsanity.com/paper/2604.16320/) (2026)
- [Collaborative Agents for Automated Program Repair in Ruby](https://mlsanity.com/paper/2511.03925/) (2025)
- [BackportBench: A Multilingual Benchmark for Automated Backporting of Patches](https://mlsanity.com/paper/2512.01396/) (2025)
- [A Dual-Loop Agent Framework for Automated Vulnerability Reproduction](https://mlsanity.com/paper/2602.05721/) (2026)
- [Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation](https://mlsanity.com/paper/2603.10072/) (2026)
- [A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks](https://mlsanity.com/paper/2604.00167/) (2026)
- [A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback](https://mlsanity.com/paper/2605.18073/) (2026)
- [Autonomous Issue Resolver: Towards Zero-Touch Code Maintenance](https://mlsanity.com/paper/2512.08492/) (2025)
- [Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis](https://mlsanity.com/paper/2604.10800/) (2026)
- [Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review](https://mlsanity.com/paper/2604.13103/) (2026)
- [A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair](https://mlsanity.com/paper/2604.21579/) (2026)
- [BLAgent: Agentic RAG for File-Level Bug Localization](https://mlsanity.com/paper/2605.17965/) (2026)
- [Efficient Skill Grounding via Code Refactoring with Small Language Models](https://mlsanity.com/paper/2606.07999/) (2026)
- [Benchmarking Large Language Models on Floating-Point Error Classification](https://mlsanity.com/paper/2606.31308/) (2026)
- [MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs](https://mlsanity.com/paper/2607.26591/) (2026)
- [Agentic Method for Deterministic Validation of Legacy Code Migration](https://mlsanity.com/paper/2607.28271/) (2026)
- [Benchmarking Automated Security Patch Backporting: How Far Are We?](https://mlsanity.com/paper/2608.17671/) (2026)
- [Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills](https://mlsanity.com/paper/2609.12012/) (2026)
- [Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution](https://mlsanity.com/paper/2609.26952/) (2026)
- [Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents](https://mlsanity.com/paper/2610.04375/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are reshaping automated program repair. We present a reproducible hierarchical taxonomy that organizes 66 LLM-based repair systems according to where repair capability and control logic principally reside: task-adapted parameters, prompt and context design, designer-specified workflows, or LLM-directed runtime control. Adaptation, generation pattern, runtime control, and auxiliary evidence are preserved as separate coded dimensions. This representation exposes control distinctions hidden by utilization labels and supports cross-paradigm analysis of system design and evaluation evidence. To the best of our knowledge, it is the first publicly available LLM-based software repair survey to operationalize Fine-Tuning, Prompting, Procedural, and Agentic as one corpus-wide primary classification. Our hierarchy complements prior surveys through one corpus-wide primary decision rule, while the result-level protocol audit bounds which reported results are defensibly comparable. To analyze how repair systems use benchmarks, we record benchmark variants, metrics, base models, and fault-localization assumptions for each system's primary reported result, identifying protocol-aligned comparison windows and benchmark-family fragments. We clarify paradigm trade-offs in task alignment, deployment cost, controllability, and multi-hunk or cross-file repair. We outline open challenges and research directions. Our artifacts and scripted survey pipeline are publicly available at https://github.com/GLEAM-Lab/ProgramRepair.