Sumon Biswas
Sumon Biswas
Home
Publication
Service
Projects
Teaching
Students
News
Talks
Blogs
Light
Dark
Automatic
Empirical Study
What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants
An empirical study of 547 real-world operational safety failures in LLM-based coding agents, revealing a taxonomy of 33 risk types and showing that over 65% of incidents arise during routine bug fixing and configuration tasks.
Alif Al Hasan
,
Sumon Biswas
Cite
ArXiv
Cite
×