评估AI agent应像研究生物行为一样，观察其动作过程。
Position: Behavioral Systems Require Behavioral Tests
- 用行为科学方法系统观察和干预AI动作
- 提出从动作序列推断决策策略的新路径
- 适合关注AI可解释性与行为机制的研究者
人工智能代理系统越来越多地作为行为系统，在动态环境中互动、追求目标并随时间适应。然而，当前评估方法主要关注性能结果，而非产生这些结果的行为过程。本文主张将AI代理像其他行为系统一样评估：通过系统观察、扰动和解读其行为。借鉴行为科学的经验，本文提出一个研究议程，包括从动作序列中恢复决策策略的方法、构建能分离行为差异的环境，以及探测多智能体系统中的涌现动态。这些方向共同为建立人工智能行为科学提供了路线图。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。