AEGIS: An Agent-based Framework for Bug Reproduction from Issue Descriptions

Automatically reproducing bugs in issue descriptions helps developers pinpoint and fix bugs timely, greatly facilitating the software development and maintenance. Built upon the powerful understanding capabilities of large language models (LLMs), agent-based approaches have achieved the state-of-the-art performance in the task. They generally leverage LLMs as the central controller to first retrieve bug-related information as context and then generate bug reproduction scripts. During the script modification process, agent-based approaches modify the script iteratively until the execution information reflects the bug accurately or the iterative turns are exhausted. Nevertheless, the agent-based approaches still face the following challenges: (1) Lengthy retrieved bug-related information: The retrieved bug-related information is usually long in length and contains irrelevant snippets, which is hard to be well comprehended by LLMs. (2) Lack of guidance in bug reproduction script generation: They generally modify bug reproduction scripts randomly and tend to generate repeated or spurious modifications, leading to bug reproduction failure.