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

TL;DR

This survey reviews recent advances in using large language models for issue resolution in software engineering, highlighting data pipelines, methodologies, challenges, and future directions, with an emphasis on the difficulty of achieving autonomous coding.

Contribution

It provides a comprehensive analysis of LLM-based issue resolution, including data collection, training techniques, and practical applications, along with identifying key challenges and future research directions.

Findings

Benchmarks like SWE-bench show LLMs struggle with issue resolution.

Training-free and training-based methods are both explored for LLMs.

Open-source resources support ongoing research in this domain.

Abstract

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.