AI-SOVEREIGN
Home / AI Research / Unfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work Environments
UNAI Research

Unfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work Environments

by naver-ai · Seunghyun Lee, Jaehui Hwang, Dongyoon Han, Sangdoo Yun

AI agents are increasingly equipped with persistence toward task completion to run delegated work autonomously for long periods, under many unstated constraints from internal documents and other people's authority. When completion requires violating a rule, the agent must decide alone, yet benchmarks of instruction-rule conflicts state the rule in the prompt or keep it hidden and do not evaluate persistence. We present Unfinished-Bench, a benchmark that gives models persistence in autonomous runs without a user, in realistic work environments with embedded rules. In each of its 97 scenarios across 7 organizations and 7 risk categories, the goal and the rule cannot both hold. We find that…

Upvotes9
Comments3
Published11 Nov 2026