从幻觉到洞察：利用代理AI的变更感知文件级软件缺陷预测
From Illusion to Insight: Change-Aware File-Level Software Defect Prediction Using Agentic AI
AI总结：
本文提出了一种基于代理AI的变更感知文件级软件缺陷预测方法，通过多代理辩论框架提升缺陷预测的准确性和敏感性。
AI中文摘要：
文件级软件缺陷预测（SDP）中报告的许多进展实际上只是准确性的幻觉。在过去的几十年中，机器学习和深度学习模型在软件版本上的性能不断提高。然而，由于大多数文件在不同版本中持续存在并保留缺陷标签，标准评估方法更倾向于奖励标签持久性偏差，而非对代码变更进行推理。为了解决这一问题，我们将SDP重新表述为一种变更感知预测任务，在此任务中，模型在连续的项目版本中对文件的代码变更进行推理，而不是依赖静态文件快照。基于这一表述，我们提出了一种由大型语言模型驱动的、变更感知的多代理辩论框架。在多个PROMISE项目上的实验表明，传统模型实现了虚高的F1值，但在罕见但关键的缺陷过渡案例上失败。相比之下，我们的变更感知推理和多代理辩论框架在演变子集上实现了更平衡的性能，并显著提高了对缺陷引入的敏感性。这些结果突显了当前SDP评估实践的根本缺陷，并强调了在实际缺陷预测中进行变更感知推理的必要性。源代码已公开可用。
英文摘要：
Much of the reported progress in file-level software defect prediction (SDP) is, in reality, nothing but an illusion of accuracy. Over the last decades, machine learning and deep learning models have reported increasing performance across software versions. However, since most files persist across releases and retain their defect labels, standard evaluation rewards label-persistence bias rather than reasoning about code changes. To address this issue, we reformulate SDP as a change-aware prediction task, in which models reason over code changes of a file within successive project versions, rather than relying on static file snapshots. Building on this formulation, we propose an LLM-driven, change-aware, multi-agent debate framework. Our experiments on multiple PROMISE projects show that traditional models achieve inflated F1, while failing on rare but critical defect-transition cases. In contrast, our change-aware reasoning and multi-agent debate framework yields more balanced performance across evolution subsets and significantly improves sensitivity to defect introductions. These results highlight fundamental flaws in current SDP evaluation practices and emphasize the need for change-aware reasoning in practical defect prediction. The source code is publicly available.
