Goodhart의 법칙을 넘어서: 다중 에이전트 시스템에서 규정 준수 평가를 위한 동적 벤치마크

[Submitted on 5 Jun 2026]

View PDF HTML (experimental)

Abstract:The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluation frameworks neglect procedural compliance, leading to ”Machiavellian” behaviors where agents strategically violate safety rules to maximize rewards – a direct manifestation of Goodhart’s Law. To address this blind spot, we introduce MAC-Bench, a dynamic, adversarial benchmark designed to evaluate the procedural alignment of multi-agent systems under realistic pressure. We propose the SERV(Seed – Evolve – Refine – Verify) pipeline, an “Agent-as-a-Benchmark” paradigm that transforms unstructured legal texts into executable, contamination-free scenarios. By synthesizing holographic sandbox environments and injecting calibrated social-engineering pressure vectors, MAC-Bench forces agents into Pareto-optimal trade-offs between task success and regulatory adherence. We introduced novel metrics: the Compliance-Weighted Success Rate (CSR) and the Machiavellian Gap (MG), and conducted a comprehensive evaluation of state-of-the-art frontier models to reveal the pervasive trade-offs between success and compliance.

Submission history

From: Yiyang Zhao [view email]
[v1] Fri, 5 Jun 2026 19:33:58 UTC (1,696 KB)