Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework

TL;DR

This paper introduces Seeker, a multi-agent framework leveraging large language models to improve exception handling in code, addressing common issues of fragility and inaccuracies in real-world software development.

Contribution

It presents the first systematic study on using LLMs with a multi-agent approach to enhance exception safety in practical coding environments.

Findings

Identified widespread issues in exception handling in real repositories.

Proposed a novel multi-agent framework inspired by expert developer strategies.

Demonstrated improved detection and resolution of exceptions using Seeker.

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.