让生成式智能体在用户不知晓时主动发现盲区，而非盲目干预。
Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight
- 从认知与行为双重角度建立主动干预的约束框架
- 提出‘认知不完备’场景下主动性的必要性与边界
- 适合研究人机协作、智能代理设计的学者与工程师
生成式AI代理通常将理解等同于回应明确问题，这种假设限制了交互范围，仅覆盖用户能表达的内容。当用户自身对缺失信息、潜在风险或值得考虑的问题缺乏意识时，该假设失效。此时，主动性不仅是效率提升，更是认知上的必要条件。我们称此为‘认知不完备’：进步依赖于与未知未知的互动以实现有效协作。现有主动方法仍局限于基于过往行为的预测，假定目标已明确定义，因而无法真正支持用户。然而，无约束地暴露新可能性可能误导注意力、使用户超载甚至造成伤害。因此，主动代理需具备行为上的合理约束——明确何时、如何以及在多大程度上介入。我们主张，生成式主动性必须同时具备认知与行为根基。结合无知哲学与主动行为研究，我们认为这些理论为设计负责任、能建立真实伙伴关系的代理提供了关键指导。
原文摘要 · Abstract (English)
Generative AI agents equate understanding with resolving explicit queries, an assumption that confines interaction to what users can articulate. This assumption breaks down when users themselves lack awareness of what is missing, risky, or worth considering. In such conditions, proactivity is not merely an efficiency enhancement, but an epistemic necessity. We refer to this condition as epistemic incompleteness: where progress depends on engaging with unknown unknowns for effective partnership. Existing approaches to proactivity remain narrowly anticipatory, extrapolating from past behavior and presuming that goals are already well defined, thereby failing to support users meaningfully. However, surfacing possibilities beyond a user's current awareness is not inherently beneficial. Unconstrained proactive interventions can misdirect attention, overwhelm users, or introduce harm. Proactive agents, therefore, require behavioral grounding: principled constraints on when, how, and to what extent an agent should intervene. We advance the position that generative proactivity must be grounded both epistemically and behaviorally. Drawing on the philosophy of ignorance and research on proactive behavior, we argue that these theories offer critical guidance for designing agents that can engage responsibly and foster meaningful partnerships.
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。