Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework
Xuanming Zhang, Yuxuan Chen, Yiming Zheng, Zhexin Zhang, Yuan Yuan, Minlie Huang
2024-12-18
Summary
This paper talks about Seeker, a new system designed to improve how computer programs handle exceptions (errors) in code, making software more reliable and robust.
What's the problem?
In software development, many programmers struggle with properly managing exceptions, which are unexpected errors that can occur during a program's execution. If exceptions are not handled correctly, it can lead to fragile code that crashes or behaves unpredictably. This problem is especially common in open-source projects, where the quality of code can vary significantly.
What's the solution?
Seeker addresses this issue by using a multi-agent framework that mimics the strategies of expert developers. It includes different agents—like Scanner, Detector, Predator, Ranker, and Handler—that work together to identify, capture, and resolve exceptions more effectively. By analyzing code and using large language models (LLMs), Seeker helps improve the way exceptions are handled, ensuring that programs are more robust and less likely to fail.
Why it matters?
This research is important because it enhances the reliability of software applications, which is crucial for both developers and users. By improving exception handling practices, Seeker can help create better-quality software that performs consistently well, reducing the chances of errors and crashes in real-world applications.
Abstract
In real world software development, improper or missing exception handling can severely impact the robustness and reliability of code. Exception handling mechanisms require developers to detect, capture, and manage exceptions according to high standards, but many developers struggle with these tasks, leading to fragile code. This problem is particularly evident in open-source projects and impacts the overall quality of the software ecosystem. To address this challenge, we explore the use of large language models (LLMs) to improve exception handling in code. Through extensive analysis, we identify three key issues: Insensitive Detection of Fragile Code, Inaccurate Capture of Exception Block, and Distorted Handling Solution. These problems are widespread across real world repositories, suggesting that robust exception handling practices are often overlooked or mishandled. In response, we propose Seeker, a multi-agent framework inspired by expert developer strategies for exception handling. Seeker uses agents: Scanner, Detector, Predator, Ranker, and Handler to assist LLMs in detecting, capturing, and resolving exceptions more effectively. Our work is the first systematic study on leveraging LLMs to enhance exception handling practices in real development scenarios, providing valuable insights for future improvements in code reliability.