ARISE工具集增强AI代理的代码故障定位和修复能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-07 04:00

研究人员开发了ARISE，一个旨在提高AI代理在软件故障定位和修复方面准确性的新系统。ARISE通过提供包含数据流信息的详细程序图来增强大型语言模型，使代理能够更精确地追踪变量使用。在SWE-bench Lite上的评估表明，与现有基线相比，故障定位和修复成功率有了显著提高。 AI

影响增强了AI代理在软件开发方面的能力，有望提高代码质量和开发人员的生产力。

排序理由这是一篇详细介绍新系统及其在基准测试上评估的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新系统及其在基准测试上评估的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 126 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Shahd Seddik, Fatemeh Fard · 2026-05-07 04:00

ARISE: 用于Agentic故障定位和程序修复的存储库级图表示和工具集

arXiv:2605.03117v1 Announce Type: cross Abstract: Repository-level fault localization (FL) and automated program repair (APR) require an agent to identify the relevant code units across files, follow call and data dependencies, and generate a valid patch. Existing graph-based sys…