Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Goodhart's Law in Reinforcement Learning
Implementing a reward function that perfectly captures a complex task in the real world is impractical. As a result, it is often appropriate to think of the reward function as a proxy for the true objective rather than a…
reinforcement-learningReinforcement LearningOn the Value of Out-of-Distribution Testing: An Example of Goodhart's Law
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set. OOD benchmarks are designed to present a different joint dis…
Model SelectionQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)Take Goodhart Seriously: Principled Limit on General-Purpose AI Optimization
A common but rarely examined assumption in machine learning is that training yields models that actually satisfy their specified objective function. We call this the Objective Satisfaction Assumption (OSA). Although devi…
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
The integration of Large Language Models (LLMs) into the financial domain is driving a paradigm shift from passive information retrieval to dynamic, agentic interaction. While general-purpose tool learning has witnessed …
Information RetrievalEvaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory standards beyond simple functional correct…