# Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement

arXiv: https://arxiv.org/abs/2503.22512 · HTML: https://mlsanity.com/paper/2503.22512/

## Key facts

- Cited by 3 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 32 of its 65 references that are in the map.
- First posted on arXiv 28 Mar 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, 30 of 32)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [An Analysis of the Automatic Bug Fixing Performance of ChatGPT](https://mlsanity.com/paper/2301.08653/) (2023)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning](https://mlsanity.com/paper/2207.08281/) (2022)
- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [A Survey of Learning-based Automated Program Repair](https://mlsanity.com/paper/2301.03270/) (2023)
- [Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair](https://mlsanity.com/paper/2309.00608/) (2023)
- [xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval](https://mlsanity.com/paper/2303.03004/) (2023)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Multilingual training for Software Engineering](https://mlsanity.com/paper/2112.02043/) (2021)
- [A Deep Dive into Large Language Models for Automated Bug Localization and Repair](https://mlsanity.com/paper/2404.11595/) (2024)
- [AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation](https://mlsanity.com/paper/2410.24117/) (2024)
- [Automatic Software Repair: a Bibliography](https://mlsanity.com/paper/1807.00515/) (2018)
- [Trust Enhancement Issues in Program Repair](https://mlsanity.com/paper/2108.13064/) (2021)
- [CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming](https://mlsanity.com/paper/2410.20527/) (2024)
- [CIRCLE: Continual Repair across Programming Languages](https://mlsanity.com/paper/2205.10956/) (2022)
- [CigaR: Cost-efficient Program Repair with LLMs](https://mlsanity.com/paper/2402.06598/) (2024)
- [ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts](https://mlsanity.com/paper/2403.06838/) (2024)
- [Verified Code Transpilation with LLMs](https://mlsanity.com/paper/2406.03003/) (2024)
- [Scalable, Validated Code Translation of Entire Projects using Large Language Models](https://mlsanity.com/paper/2412.08035/) (2024)
- [When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair](https://mlsanity.com/paper/2412.01072/) (2024)
- [Fixing Rust Compilation Errors using LLMs](https://mlsanity.com/paper/2308.05177/) (2023)

## Built on by (most cited first, 3 of 3)

- [EffiReasonTrans: RL-Optimized Reasoning for Code Translation](https://mlsanity.com/paper/2510.18863/) (2025)
- [Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation](https://mlsanity.com/paper/2509.19918/) (2025)
- [Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs](https://mlsanity.com/paper/2605.28388/) (2026)

## Abstract (arXiv)

Recent advances in leveraging LLMs for APR have demonstrated impressive capabilities in fixing software defects. However, current LLM-based approaches predominantly focus on mainstream programming languages like Java and Python, neglecting less prevalent but emerging languages such as Rust due to expensive training resources, limited datasets, and insufficient community support. This narrow focus creates a significant gap in repair capabilities across the programming language spectrum, where the full potential of LLMs for comprehensive multilingual program repair remains largely unexplored. To address this limitation, we introduce a novel cross-language program repair approach LANTERN that leverages LLMs' differential proficiency across languages through a multi-agent iterative repair paradigm. Our technique strategically translates defective code from languages where LLMs exhibit weaker repair capabilities to languages where they demonstrate stronger performance, without requiring additional training. A key innovation of our approach is an LLM-based decision-making system that dynamically selects optimal target languages based on bug characteristics and continuously incorporates feedback from previous repair attempts. We evaluate our method on xCodeEval, a comprehensive multilingual benchmark comprising 5,068 bugs across 11 programming languages. Results demonstrate significant enhancement in repair effectiveness, particularly for underrepresented languages, with Rust showing a 22.09% improvement in Pass@10 metrics. Our research provides the first empirical evidence that cross-language translation significantly expands the repair capabilities of LLMs and effectively bridges the performance gap between programming languages with different levels of popularity, opening new avenues for truly language-agnostic automated program repair.