IEEE Transactions on Software Engineering最新文献_第7页

Updating While Comparing: Dynamic User Feedback Prioritization enhanced by Knowledge Tracing 边比较边更新：知识追踪增强的动态用户反馈优先级

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-21 DOI: 10.1109/tse.2026.3726191

Haiyi Liu, Ying Jiang, Yaohan Ji, Zejiang Zhao

引用次数: 0

A Needle in a Haystack: Intent-driven Reusable Artifacts Recommendation with LLMs 大海捞针：llm的意图驱动的可重用工件推荐

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-21 DOI: 10.1109/tse.2026.3725008

Dongming Jin, Zhi Jin, Xiaohong Chen, Linyu Li, Zheng Fang, Yuanpeng He, Jia Li, Yiran Zhang, Yingtao Fang

引用次数: 0

Formalisms for Robotic Mission Specification and Execution: A Comparative Analysis 机器人任务规范与执行的形式化：比较分析

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-21 DOI: 10.1109/tse.2026.3725356

Gianluca Filippone, Sara Pettinari, Patrizio Pelliccione

引用次数: 0

SCG-Agent: A Scheduler-Driven Code Generation Framework with Multi-Checker SCG-Agent：带有多检查器的调度程序驱动的代码生成框架

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-20 DOI: 10.1109/tse.2026.3725731

Yinan Chen, Yuan Huang, Xiangping Chen, Zibin Zheng

引用次数: 0

Towards Robust Android Malware Detection under Concept Drift and Code Obfuscation 基于概念漂移和代码混淆的稳健Android恶意软件检测

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-20 DOI: 10.1109/tse.2026.3725737

Hailong Yu, Tiantian Wang, Lwin Khin Shar, Jiakun Liu, David Lo

引用次数: 0

SNIPTEST: Fuzzing Multi-Level Code Slices for Validating Vulnerabilities SNIPTEST：模糊多级代码片以验证漏洞

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-19 DOI: 10.1109/tse.2026.3725696

Aniruddhan Murali, Noble Saji Mathews, Mahmoud Alfadel, Meng Xu, Meiyappan Nagappan

引用次数: 0

When Model Editing Meets Service Evolution: A Knowledge-Update Perspective for Service Recommendation 当模型编辑遇到服务演化：服务推荐的知识更新视角

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-17 DOI: 10.1109/tse.2026.3724627

Guodong Fan, Cuiyun Gao, Chun Yong Chong, Lu Zhang, Jing Li, Jinglin Zhang, Shizha Chen

引用次数: 0

Understanding Prompt Quality and Its Relation to LLM-based Code Generation 理解提示质量及其与基于llm的代码生成的关系

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-03 DOI: 10.1109/tse.2026.3719766

Antonio Della Porta, Stefano Lambiase, Valeria Pontillo, Joao F. Ferreira, Akond A. Rahman, Chaiyong Ragkhitwetsagul, Fabio Palomba

引用次数: 0

An Empirical Study of Kotlin-Java Cross-Dependency Issues and Their Detection Kotlin-Java交叉依赖问题及其检测的实证研究

IF 7.4 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-03 DOI: 10.1109/tse.2026.3719845

Qiong Feng, Xiaotian Ma, Jiayi Sheng, Huan Ji, Peng Liang

引用次数: 0

EffiReasonTrans: RL-Optimized Reasoning for Code Translation EffiReasonTrans：代码翻译的rl优化推理

IF 6 1区计算机科学

IEEE Transactions on Software Engineering Pub Date : 2026-08-01 Epub Date: 2026-03-15 DOI: 10.1109/TSE.2026.3693795

Yanlin Wang;Rongyi Ou;Yanli Wang;Mingwei Liu;Jiachi Chen;Ensheng Shi;Xilin Liu;Yuchi Ma;Zibin Zheng

{"title":"EffiReasonTrans: RL-Optimized Reasoning for Code Translation","authors":"Yanlin Wang;Rongyi Ou;Yanli Wang;Mingwei Liu;Jiachi Chen;Ensheng Shi;Xilin Liu;Yuchi Ma;Zibin Zheng","doi":"10.1109/TSE.2026.3693795","DOIUrl":"10.1109/TSE.2026.3693795","url":null,"abstract":"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, which also helps balance inference latency. We evaluate EffiReasonTrans on six translation pairs. Experimental results show that EffiReasonTrans 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 shows improvements of translation accuracy when integrated into agent-based frameworks. Our code and data are available at <uri>https://github.com/DeepSoftwareAnalytics/EffiReasonTrans</uri>.","PeriodicalId":13324,"journal":{"name":"IEEE Transactions on Software Engineering","volume":"52 8","pages":"2354-2366"},"PeriodicalIF":6.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148291572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0