# REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring

arXiv: https://arxiv.org/abs/2608.23611 · HTML: https://mlsanity.com/paper/2608.23611/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [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)
- [Agentic Refactoring: An Empirical Study of AI Coding Agents](https://mlsanity.com/paper/2511.04824/) (2025)
- [SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring](https://mlsanity.com/paper/2602.03712/) (2026)
- [An Empirical Study on the Potential of LLMs in Automated Software Refactoring](https://mlsanity.com/paper/2411.04444/) (2024)
- [RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring](https://mlsanity.com/paper/2511.03153/) (2025)
- [From Restructuring to Stabilization: A Large-Scale Experiment on Iterative Code Readability Refactoring with Large Language Models](https://mlsanity.com/paper/2602.21833/) (2026)
- [SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair](https://mlsanity.com/paper/2605.07001/) (2026)
- [RefModel: Detecting Refactorings using Foundation Models](https://mlsanity.com/paper/2507.11346/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems without introducing new issues or altering behaviour-relevant code structures. We introduce REFINE (Refactoring with Evidence-aware Flow for Integrated ageNtic Execution), a tool-agnostic, evidence-aware multi-agent approach for generating Java file-level refactoring candidates. REFINE combines static-analysis-guided smell identification, smell-informed planning, LLM-based transformation, automated re-analysis, preservation checks, and structured reporting. We evaluate REFINE on 450 Java files from 15 open-source systems, producing 1,350 model-pass outputs using OpenAI GPT-5.5, Google Gemini 3.1 Pro Preview, and Anthropic Claude Opus 4.8. REFINE reduces detected code smells by 68.26%, 72.79%, and 68.49% across the three configurations, respectively, with the strongest reductions observed for major smells. A matched 150-file direct-prompt baseline shows that REFINE achieves a higher median code-smell reduction with smaller edits and fewer public-method removals. However, broader quality improvements are inconsistent, and preservation checks reveal residual risks, including assert/fail-call changes and public-method removal. Therefore, REFINE outputs should be treated as refactoring candidates requiring compilation, testing, dependency analysis, and human review before adoption in repository- or system-level settings.