Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs
Computer Science > Artificial Intelligence arXiv:2512.20798 (cs) [Submitted on 23 Dec 2025 (v1), last revised 1 Feb 2026 (this version, v2)] Title:A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents Authors:Miles Q. Li, Benjamin C. M. Fung, Martin Weiss, Pulei Xiong, Khalil Al-Hussaeni, Claude Fachkha View a PDF of the paper titled A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents, by Miles Q. Li and 5 other authors View PDF HTML (experimental) Abstract:As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has become a paramount concern. Current safety benchmarks primarily evaluate whether agents refuse explicitly harmful…
