1
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
首个针对LLM根因诊断的日志缩减基准，评估工具在海量噪音CI日志中的降噪效果，提升编码代理调试效率。
arXiv:2605.28876v1 Announce Type: cross Abstract: CI failure logs are large (median 5k lines, max 200k in this corpus) and noisy. Coding agents that t…