为可问责AI系统设计了衡量功能意图的量化框架
Intentionality is a Design Decision: Measuring Functional Intentionality for Accountable AI Systems
- 提出五维可测的行为指标，评估AI是否像有目的的行动者
- 通过测试框架识别系统在目标追求中的组织性与持续性表现
- 适合关注AI责任归属与自主性调控的研究者与开发者
随着AI系统表现出越来越多自主、目标导向和长周期行为，用户缺乏标准化方法来判断其在治理与问责中是否具备类似意图行为。本文不将意图等同于意识，而是将其定义为包含目的性、预见性、意志力、时间承诺和连贯性的行为特征，这些标准长期用于法律与哲学领域推断意图。这些特性由系统设计决定：如记忆持久性、规划深度和工具自主性等架构选择，决定了系统展现有序目标追求的程度。若意图具有设计依赖性，则原则上可控制；而控制需以测量为基础。本文提出功能性意图测试（FIT），一个跨五维度的量化框架，用于衡量意图类行为，并设计了结构化评估协议FIT-Eval，以生成评分。人类代理减少可提升效率，但意图能力上升会增加问责风险。通过将意图转化为可解释的层级，FIT实现对日益自主系统的适度监管与自主性精细调节。
原文摘要 · Abstract (English)
As AI systems increasingly exhibit autonomous, goal-directed, and long-horizon behavior, users lack a standardized way to detect the degree to which a system functions like an intentional actor for governance and accountability purposes. This position paper defines intentionality not as consciousness, but as a behavioral profile characterized by purpose, foresight, volition, temporal commitment, and coherence - criteria long used in legal and philosophical contexts to infer intent. These properties are design-contingent: architectural choices such as memory persistence, planning depth, and tool autonomy shape the degree to which systems exhibit organized goal pursuit. If intentionality is design-contingent, it is in principle controllable. Yet control requires measurement. We introduce the Functional Intentionality Test (FIT), a multidimensional framework that quantifies intentional-like behavior across five observable dimensions, and propose FIT-Eval, a structured evaluation protocol for eliciting and scoring them. While reduced human agency can increase efficiency, rising intentional capacity heightens accountability risks. By translating intentionality into interpretable levels, FIT enables proportionate oversight and deliberate autonomy calibration in increasingly agentic systems.
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。