Agentic Software Issue Resolution with Large Language Models: A Survey

TL;DR

This survey reviews 126 recent studies on LLM-based agentic systems for software issue resolution, emphasizing their workflow, taxonomy, and the paradigm shift introduced by agentic reinforcement learning, highlighting future challenges and directions.

Contribution

It provides a comprehensive taxonomy and analysis of recent advancements in agentic LLM-based software issue resolution, including a focus on reinforcement learning approaches.

Findings

Agentic systems improve software maintenance efficiency.

Reinforcement learning has shifted system design paradigms.

The survey identifies key challenges and future research directions.

Abstract

Software issue resolution aims to address real-world issues in software repositories (e.g., bug fixing and efficiency optimization) based on natural language descriptions provided by users, representing a key aspect of software maintenance. With the rapid development of large language models (LLMs) in reasoning and generative capabilities, LLM-based approaches have made significant progress in automated software issue resolution. However, real-world software issue resolution is inherently complex and requires long-horizon reasoning, iterative exploration, and feedback-driven decision making, which demand agentic capabilities beyond conventional single-step approaches. Recently, LLM-based agentic systems have become mainstream for software issue resolution. Advancements in agentic software issue resolution not only greatly enhance software maintenance efficiency and quality but also provide a realistic environment for validating agentic systems' reasoning, planning, and execution capabilities, bridging artificial intelligence and software engineering. This work presents a systematic survey of 126 recent studies at the forefront of LLM-based agentic software issue resolution research. It outlines the general workflow of the task and establishes a taxonomy across three dimensions: benchmarks, techniques, and empirical studies. Furthermore, it highlights how the emergence of agentic reinforcement learning has brought a paradigm shift in the design and training of agentic systems for software engineering. Finally, it summarizes key challenges and outlines promising directions for future research.