Papers
arxiv:2510.18863

EffiReasonTrans: RL-Optimized Reasoning for Code Translation

Published on Oct 21
Authors:
,
,
,
,
,
,
,
,

Abstract

EffiReasonTrans, a two-stage training framework, enhances code translation accuracy and reduces inference latency by using a reasoning-augmented dataset and reinforcement learning.

AI-generated summary

Code translation is a crucial task in software development and maintenance. While recent advancements in large language models (LLMs) have improved automated code translation accuracy, these gains often come at the cost of increased inference latency, hindering real-world development workflows that involve human-in-the-loop inspection. To address this trade-off, we propose EffiReasonTrans, a training framework designed to improve translation accuracy while balancing inference latency. We first construct a high-quality reasoning-augmented dataset by prompting a stronger language model, DeepSeek-R1, to generate intermediate reasoning and target translations. Each (source code, reasoning, target code) triplet undergoes automated syntax and functionality checks to ensure reliability. Based on this dataset, we employ a two-stage training strategy: supervised fine-tuning on reasoning-augmented samples, followed by reinforcement learning to further enhance accuracy and balance inference latency. We evaluate EffiReasonTrans on six translation pairs. Experimental results show that it consistently improves translation accuracy (up to +49.2% CA and +27.8% CodeBLEU compared to the base model) while reducing the number of generated tokens (up to -19.3%) and lowering inference latency in most cases (up to -29.0%). Ablation studies further confirm the complementary benefits of the two-stage training framework. Additionally, EffiReasonTrans demonstrates improved translation accuracy when integrated into agent-based frameworks. Our code and data are available at https://github.com/DeepSoftwareAnalytics/EffiReasonTrans.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.18863 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.18863 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.18863 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.