这篇论文把AI行为拆成两层来诊断，教你看清行为是来自模型结构还是外部规则，对搞智能体评估和治理的人很有用。
该论文提出一个名为"层归因"的框架，将AI智能体行为分析分为基础计算层（架构、记忆、感知、注意力、表征）和行为调节层（身份、资源、目标、社会互动、制度约束、治理）。框架指出三个关键结论：替代有效性是模型-任务-层的关系，人机差异提供诊断证据，治理需在干预前进行源头归因。该框架为评估AI智能体行为来源提供了系统性方法。
A Diagnostic Framework for AI Agent Behavior
AI agents increasingly act within the same clinical, political, scientific, and social systems that behavioral scientists study. Evaluating these systems requires source-level diagnosis: the same behavioral pattern may arise from an agent representational substrate or from the roles, objectives, interaction structures, and governance rules that shape its expression. This Perspective proposes a diagnostic framework for AI agent behavior: layer attribution. The foundational computational layer defines what behaviors are possible through architecture, memory, perception, attention, and representation. The behavioral modulation layer shapes how those capacities are expressed through identity, resources, objectives, social interaction, institutional constraints, and governance. The framework clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention. Treating AI agents as behavioral actors therefore requires evaluation methods that determine where behavior originates before deciding how to explain, validate, or govern it.