跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19554 · v1

Inquest: Log-Guided Root-Cause Code Localization with a Staged Agent

首次提交 2026-11-15 02:39
版本更新 2026-11-15 02:39
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

When a production issue is reported, engineers get a description and some logs, but no failing test and no way to reproduce the fault. The logs show where the failure was noticed, not where it was caused: in 49% of the real reports we study, the text names none of the files that the fix later changed. We built a benchmark for this setting from two public datasets and 27 open-source projects (Apache, Red Hat, MongoDB, MariaDB, Qt and Sakai). It holds 38,001 resolved issue reports with their pasted logs, the code as it was while the bug was still present, and the files the fix changed. We present INQUEST, an agent that finds the faulty code using a 27B open-weights model. Code, not the model, controls the procedure. It first gathers the evidence, including the files fixed in similar past issues that were resolved before the report was filed. The model then makes only three bounded decisions: which files to open, what role each file plays in the failure, and how to rank them. On 26,544 evaluation reports, INQUEST ranks a changed file first for 68.6% and in the top five for 85.9%, names the correct module for 90.2%, and ranks a changed function first for 53.8%. On the reports that name no faulty file, it reaches 52.8% and 73.6%. A free agent loop with the same model and tools finds files equally well, but names the faulty function 14 points less often. On a 1,000-report sample, INQUEST beats our reimplementations of two published agents by 7 and 20 points of top-1 accuracy (4 and 16 counting only the reports those agents answered), and the same model used as a re-ranker by 6. We report the cost of every system and the results that go against us, and we release the benchmark, both systems and every run transcript.

作者备注:12 pages, 2 figures, 6 tables. Submitted to the ICSE 2027 Industry Challenge track. Benchmark: https://doi.org/10.5281/zenodo.24217071 ; code, results and run transcripts: https://doi.org/10.5281/zenodo.24217136

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 02:39 · 最新观测版本

Inquest: Log-Guided Root-Cause Code Localization with a Staged Agent

When a production issue is reported, engineers get a description and some logs, but no failing test and no way to reproduce the fault. The logs show where the failure was noticed, not where it was caused: in 49% of the real reports we study, the text names none of the files that the fix later changed. We built a benchmark for this setting from two public datasets and 27 open-source projects (Apache, Red Hat, MongoDB, MariaDB, Qt and Sakai). It holds 38,001 resolved issue reports with their pasted logs, the code as it was while the bug was still present, and the files the fix changed. We present INQUEST, an agent that finds the faulty code using a 27B open-weights model. Code, not the model, controls the procedure. It first gathers the evidence, including the files fixed in similar past issues that were resolved before the report was filed. The model then makes only three bounded decisions: which files to open, what role each file plays in the failure, and how to rank them. On 26,544 evaluation reports, INQUEST ranks a changed file first for 68.6% and in the top five for 85.9%, names the correct module for 90.2%, and ranks a changed function first for 53.8%. On the reports that name no faulty file, it reaches 52.8% and 73.6%. A free agent loop with the same model and tools finds files equally well, but names the faulty function 14 points less often. On a 1,000-report sample, INQUEST beats our reimplementations of two published agents by 7 and 20 points of top-1 accuracy (4 and 16 counting only the reports those agents answered), and the same model used as a re-ranker by 6. We report the cost of every system and the results that go against us, and we release the benchmark, both systems and every run transcript.

查看此版本解读 →查看此版本原文 ↗