# RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring

arXiv: https://arxiv.org/abs/2511.03153 · HTML: https://mlsanity.com/paper/2511.03153/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 57 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 14 of 14)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration](https://mlsanity.com/paper/2406.01422/) (2024)
- [MASAI: Modular Architecture for Software-engineering AI Agents](https://mlsanity.com/paper/2406.11638/) (2024)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing](https://mlsanity.com/paper/2409.10737/) (2024)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)
- [An Empirical Study on the Code Refactoring Capability of Large Language Models](https://mlsanity.com/paper/2411.02320/) (2024)
- [Code Smells and Refactoring: A Tertiary Systematic Review of Challenges and Observations](https://mlsanity.com/paper/2004.10777/) (2020)
- [Fixing Large Language Models' Specification Misunderstanding for Better Code Generation](https://mlsanity.com/paper/2309.16120/) (2023)
- [20-MAD -- 20 Years of Issues and Commits of Mozilla and Apache Development](https://mlsanity.com/paper/2003.14015/) (2020)
- [On Preserving the Behavior in Software Refactoring: A Systematic Mapping Study](https://mlsanity.com/paper/2106.13900/) (2021)

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

- [Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement](https://mlsanity.com/paper/2609.01481/) (2026)
- [SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair](https://mlsanity.com/paper/2605.07001/) (2026)
- [A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX](https://mlsanity.com/paper/2603.27296/) (2026)
- [Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search](https://mlsanity.com/paper/2605.20244/) (2026)
- [SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements](https://mlsanity.com/paper/2607.27409/) (2026)
- [REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring](https://mlsanity.com/paper/2608.23611/) (2026)
- [Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase](https://mlsanity.com/paper/2608.29310/) (2026)
- [Concealing LLM-Based Multi-Agent Topology via Phantom Structure Injection](https://mlsanity.com/paper/2609.37567/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs have shown the ability to reduce development time and enhance code quality. However, these LLMs often rely on static, detailed instructions for specific tasks. In contrast, LLM-based agents can dynamically adapt to evolving contexts and autonomously make decisions by interacting with software tools and executing workflows. In this paper, we explore the potential of LLM-based agents in supporting refactoring activities. Specifically, we introduce RefAgent, a multi-agent LLM-based framework for end-to-end software refactoring. RefAgent consists of specialized agents responsible for planning, executing, testing, and iteratively refining refactorings using self-reflection and tool-calling capabilities. We evaluate RefAgent on eight open-source Java projects, comparing its effectiveness against a single-agent approach, a search-based refactoring tool, and historical developer refactorings. Our assessment focuses on: (1) the impact of generated refactorings on software quality, (2) the ability to identify refactoring opportunities, and (3) the contribution of each LLM agent through an ablation study. Our results show that RefAgent achieves a median unit test pass rate of 90%, reduces code smells by a median of 52.5%, and improves key quality attributes (e.g., reusability) by a median of 8.6%. Additionally, it closely aligns with developer refactorings and the search-based tool in identifying refactoring opportunities, attaining a median F1-score of 79.15% and 72.7%, respectively. Compared to single-agent approaches, RefAgent improves the median unit test pass rate by 64.7% and the median compilation success rate by 40.1%. These findings highlight the promise of multi-agent architectures in advancing automated software refactoring.