Abstract
The rise of generative and autonomous agents marks a fundamental shift in computing, demanding a rethinking of how humans collaborate with probabilistic, partially autonomous systems. We present the Human-AI-Experience (HAX) framework, a comprehensive, three-phase approach that establishes design foundations for trustworthy, transparent, and collaborative agentic interaction. HAX integrates behavioral heuristics, a schema-driven SDK enforcing structured and safe outputs, and a behavioral proxy concept that orchestrates agent activity to reduce cognitive load. A validated catalog of mixed-initiative design patterns further enables intent preview, iterative alignment, trust repair, and multi-agent narrative coherence. Grounded in Time, Interaction, and Performance (TIP) theory, HAX reframes multi-agent systems as colleagues, offering the first end-to-end framework that bridges trust theory, interface design, and infrastructure for the emerging Internet of Agents.
Abstract (translated)
生成式和自主代理的兴起标志着计算领域的根本性转变，这要求我们重新思考人类如何与概率性和部分自治系统合作。本文介绍了Human-AI-Experience（HAX）框架，这是一个全面、分三阶段的方法，旨在为可信、透明且协作性的代理交互建立设计基础。HAX集成了行为启发式、一个基于模式的SDK以强制执行结构化和安全的输出以及一种行为代理概念，该概念通过减少认知负荷来协调代理活动。经过验证的设计模式目录进一步支持了意图预览、迭代对齐、信任修复和多代理叙述连贯性等功能。HAX植根于时间、交互与性能（TIP）理论，将多代理系统重新定义为同事关系，并提供了首个端到端框架，该框架连接了信任理论、界面设计以及新兴的代理人互联网所需的基础设施。
URL
https://arxiv.org/abs/2512.11979
