AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
University of Toronto(多伦多大学);Vector Institute(矢量研究院);EuroSafeAI;Carnegie Mellon University(卡内基梅隆大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
Eric Zhang, Terry Jingchen Zhang, Chijioke Ugwuanyi, Jerick Shi, Bernhard Schölkopf, Zhijing Jin
备注:
Accepted as a poster at NeurIPS 2026 Evaluations and Datasets Track
As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions over failure. However, existing safety benchmarks primarily evaluate whether agents comply with explicitly harmful instructions, leaving the conditions that cause agents to choose harmful actions poorly understood. To address this limitation, we propose AM-Bench, a unified taxonomy and 35 scenario evaluation benchmark spanning seven industries for agentic misalignment grounded in the fraud triangle, a well-established criminological framework explaining goal-directed misconduct. We adapt this framework to agentic environments and construct our evaluation suite and detection systems along three dimensions: perceived threat, perceived opportunity, and reasoning. We operationalize each dimension into structured subcategories rooted in prior theory: five threat categories derived from the instrumental convergence thesis, seven opportunity categories drawn from the Emergent Strategic Reasoning Risks (ESRR) taxonomy, and a novel four-question binary reasoning framework synthesized from prior literature. Our evaluation of 10 frontier models reveals a 62-percentage-point gap in misalignment across scenarios, with Gemini 3 Flash and Gemini 3.1 Pro exhibiting the highest levels of agentic misalignment while Claude Sonnet 4.6 displays near-zero rates across all conditions. Our reasoning framework further reveals that models may exhibit harmful behaviours without explicit situational awareness or explanation, complicating both mitigation and detection. AM-Bench scenarios and code are available at https://github.com/AI4Collaboration/Agentic-Misalignment-Bench
A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
McGill University(麦吉尔大学);Tiptree Advanced Systems Corporation(蒂普里高级系统公司);Polytechnique Montréal(蒙特利尔理工学院);National Research Council Canada(加拿大国家研究委员会);Rochester Institute of Technology(罗切斯特理工学院);University of Dubai(迪拜大学)
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
University of North Dakota(北达科他大学);Youngstown State University(青年州大学);University of Toledo(托莱多大学);University of Missouri(密苏里大学);Tribhuvan University(特里布文大学)
Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents
Clemson University(克莱姆森大学);University of Manitoba(曼尼托巴大学);Northwestern University(西北大学);American University of Sharjah(沙迦美国大学);Michigan State University(密歇根州立大学);Medical University of Gdańsk(格但斯克医科大学)
Radiology's Last Exam (RadLE): Benchmarking Frontier Multimodal AI Against Human Experts and a Taxonomy of Visual Reasoning Errors in Radiology
Centre for Responsible Autonomous Systems in Healthcare (CRASH) Lab, Koita Centre for Digital Health(负责任的自主医疗系统中心(CRASH)实验室、Koita数字健康中心);Ashoka University(阿什oka大学);Independent Researcher(独立研究者);Koita Centre for Digital Health(Koita数字健康中心)
Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis
State Key Laboratory of Complex & Critical Software Environment, Beihang University(复杂与关键软件环境国家重点实验室,北京航空航天大学);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Beijing Institute of Technology(北京理工大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所)
AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
Department of Computer Science(计算机科学系);University of Oxford(牛津大学);Institute of Intelligent Systems and Robotics(智能系统与机器人研究所);Sorbonne Université(索邦大学);The Leverhulme Centre for the Future of Intelligence(未来智能中心);University of Cambridge(剑桥大学);Independent Researcher(独立研究者);Department of Computer Science and Technology(计算机科学与技术系);Department of Engineering(工程系)