Preprint
Oct 2026
V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents
Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution, and highlighting the need to move beyond risk recognition toward enforcing safety throughout execution.
Wei-Tao Feng, Heng-Heng Xiong, Zi-Hao Zeng et al.
· 0 citations