[论文解读] Visioning Human-Agentic AI Teaming: Continuity, Tension, and Future Research

Bowen Lou, Tian Lu+2 more|arXiv (Cornell University)|Mar 5, 2026

Embodied and Extended Cognition被引用 2

一句话总结

该论文将团队态势感知（Team SA）扩展到具开放性自我驱动的 AI，考察连续性与张力如何影响长期对齐，并提出人-代理 AI 协作的研究议程。

ABSTRACT

Artificial intelligence is undergoing a structural transformation marked by the rise of agentic systems capable of open-ended action trajectories, generative representations and outputs, and evolving objectives. These properties introduce structural uncertainty into human-AI teaming (HAT), including uncertainty about behavior trajectories, epistemic grounding, and the stability of governing logics over time. Under such conditions, alignment cannot be secured through agreement on bounded outputs; it must be continuously sustained as plans unfold and priorities shift. We advance Team Situation Awareness (Team SA) theory, grounded in shared perception, comprehension, and projection, as an integrative anchor for this transition. While Team SA remains analytically foundational, its stabilizing logic presumes that shared awareness, once achieved, will support coordinated action through iterative updating. Agentic AI challenges this presumption. Our argument unfolds in two stages: first, we extend Team SA to reconceptualize both human and AI awareness under open-ended agency, including the sensemaking of projection congruence across heterogeneous systems. Second, we interrogate whether the dynamic processes traditionally assumed to stabilize teaming in relational interaction, cognitive learning, and coordination and control continue to function under adaptive autonomy. By distinguishing continuity from tension, we clarify where foundational insights hold and where structural uncertainty introduces strain, and articulate a forward-looking research agenda for HAT. The central challenge of HAT is not whether humans and AI can agree in the moment, but whether they can remain aligned as futures are continuously generated, revised, enacted, and governed over time.

研究动机与目标

• 定义代理性 AI 如何引入开放性行动、表示与目标进化，导致传统的人机协同对齐（HAT）失稳。
• 将团队态势感知扩展为重新构想在开放性代理下的人与 AI 的感知。
• 评估动态过程（关系互动、学习、协调）是否使具自适应自主性的协作保持稳定还是被破坏。
• 区分连续性与张力，以绘制现有洞见的适用范围与新问题的出现点。
• 为未来在代理性 AI 下的 HAT 研究提出结构化的研究议程。

提出的方法

• 在理论层面将团队态势感知与开放性代理整合，以重新解读人类与 AI 的感知 Level 1–3、理解和投射。
• 映射评估性态度理论、关系互动、认知学习、解释性引导、集体协调和操作控制如何与 HAT 中的团队态势感知层级对齐。
• 引入投射一致性作为跨系统对齐的关键度量，衡量人类与 AI 对未来的预期在时间上的一致性。
• 建立连续性–张力框架，识别开放性 HAT 中的稳定与破坏性动态。
• 提出研究问题（RQ1.1–RQ1.4）及一阶问题，引导对轨迹解释、表示一致性与投射一致性的实证研究。

实验结果

研究问题

• RQ1 RQ1.1 指标如何捕捉人类对 AI 启动的轨迹变化与隐含承诺的解读？
• RQ2 RQ1.2 如何评估在人类构建的任务表示在展开的中间状态下的连贯性与稳定性？
• RQ3 RQ1.3 如何在分支未来与目标优先级变化中评估投射一致性？
• RQ4 RQ1.4 任务特征如何影响这些评估过程的鲁棒性？

主要发现

• 开放性代理可能颠覆典型的 Team SA 益处，使关系正当性依赖于认知脆弱性，迭代更新会放大分歧。
• 当人类与 AI 预测目标与治理优先级随未来变化时，投射一致性变得至关重要。
• 在开放性代理下，AI 的感知（感知、理解、投射）必须可观测且可互操作，以评估跨系统对齐。
• 连续性在静态、较低的 Team SA 层级中仍然存在，但在轨迹与治理机制演化的动态层次上会出现张力。
• 论文提出了一个研究议程，用以检验关系互动、学习与协调在代理性自治下如何产生稳定或不稳定。