基於大型語言模型的軟件工程問題解決進展與前沿：全面綜述

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey

January 15, 2026

作者: Caihua Li, Lianghong Guo, Yanlin Wang, Daya Guo, Wei Tao, Zhenyu Shan, Mingwei Liu, Jiachi Chen, Haoyu Song, Duyu Tang, Hongyu Zhang, Zibin Zheng

cs.AI

摘要

問題修復作為軟體工程中一項複雜的現實開發任務，已成為人工智慧領域備受關注的挑戰。SWE-bench等基準測試的建立表明，該任務對大型語言模型而言極具難度，這顯著加速了自主編碼代理的發展進程。本文針對這一新興領域展開系統性綜述：首先剖析數據建構流程，涵蓋自動化收集與合成方法；繼而全面分析技術方法，從具備模組化組件的免訓練框架，到基於訓練的技術（包括監督式微調與強化學習）；接著探討數據質量與代理行為的關鍵分析，並結合實際應用場景展開討論；最後指出核心挑戰並勾勒未來研究的潛在方向。為持續推動該領域發展，我們在https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution維護開源資源庫作為動態知識樞紐。

English

Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as profoundly difficult for large language models, thereby significantly accelerating the evolution of autonomous coding agents. This paper presents a systematic survey of this emerging domain. We begin by examining data construction pipelines, covering automated collection and synthesis approaches. We then provide a comprehensive analysis of methodologies, spanning training-free frameworks with their modular components to training-based techniques, including supervised fine-tuning and reinforcement learning. Subsequently, we discuss critical analyses of data quality and agent behavior, alongside practical applications. Finally, we identify key challenges and outline promising directions for future research. An open-source repository is maintained at https://github.com/DeepSoftwareAnalytics/Awesome-Issue-Resolution to serve as a dynamic resource in this field.