Software Engineering Empirical Research Radar

Finding the Needle in the Crash Stack: Industrial-Scale Crash Root Cause Localization with AutoCrashFL

Paper detail page in SEER Radar.

Authors

Sungmin Kang, Sumi Yun, Jingun Hong, Shin Yoo, Gabin An

Venue / Year

ICSE-SEIP 2026

Topics

Debugging / Fault Localization / Diagnosis / Repair; AI / LLM for SE; Industrial Software Engineering

Abstract / Summary

AutoCrashFL is an LLM agent for industrial crash root-cause localization that requires only a crash dump and access to the corresponding source repository, avoiding per-execution coverage collection for large software systems.

External Links

Official / Source Page

PDF

Local PDF is not available on SEER Radar yet. When a public source is recorded, this page will add a local reading link with source attribution.