定位：行为系统需要行为测试
Position: Behavioral Systems Require Behavioral Tests
浏览论文内容
中文总结 AI 辅助
本文提出AI智能体需如其他行为系统般接受评估，借鉴行为科学提出含行为测试开发等内容的研究议程，为AI行为科学发展提供路线图。
中文摘要 AI 辅助
人工智能体系统日益作为行为系统运行，通过与动态环境交互、追求目标并随时间适应。然而，当前评估方法主要聚焦于性能结果，而非产生结果的潜在行为过程。本文主张，AI智能体必须像其他行为系统一样接受评估：通过对其行为进行系统观察、扰动和解读。我们借鉴行为科学的经验来支撑这一立场，并提出一项研究议程，重点开发严格的行为测试，包括从行为序列中恢复决策策略、构建能隔离行为差异的环境，以及探测多智能体系统中的涌现动态。总体而言，这些方向为开发AI行为科学提供了路线图。
英文摘要
Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behavioral processes that produce them. This paper argues that AI agents must be evaluated like other behavioral systems: through systematic observation, perturbation, and interpretation of their actions. We draw on lessons from the behavioral sciences to motivate this position, and propose a research agenda focused on developing rigorous behavioral tests. These include methods for recovering decision strategies from action sequences, constructing environments that isolate behavioral differences, and probing emergent dynamics in multi-agent systems. Taken together, these directions offer a roadmap for developing a science of AI behavior.
