LLM-based multi-agent systems increasingly coordinate planning, reasoning, tool use, and human interaction, yet their reliability remains limited. A central source of this limitation is the underspecified prompt--harness boundary. Current systems lack a principled way to decide which workflow commitments should remain in prompts and which should become harness structure. We present \textbf{XFlow}, an executable protocol programming system for reliable multi-agent workflows, and \textbf{XPF} (XFlow Protocol Format), its domain-specific protocol programming language. XFlow occupies a middle position between prompt-only orchestration and markup-like workflow descriptions. XPF remains readable as a literate protocol, but it is compiled and executed as a program. Its design keeps informal semantic work inside actors while moving selected commitments into harness structure that can be checked, preserved, and enforced. At runtime, XFlow stages uncertainty through lifecycle-governed symbols, which are typed state cells with validation and commit states. Actor outputs are mediated before they become shared state, instead of spreading through prompts, transcripts, or implicit memory. Our experiments cover Constrained Interaction, Long-Context Reasoning, and Agentic Software Engineering. They show that XFlow improves reliability by making constraints, evidence handling, and process requirements explicit and enforceable.

翻译：基于大语言模型的多智能体系统日益协调规划、推理、工具使用与人类交互，但其可靠性仍存在局限。这一局限的核心根源在于提示-硬边界（prompt-harness boundary）的欠指定性。当前系统缺乏原则性方法来决定哪些工作流承诺应保留在提示中，哪些应转化为硬结构。我们提出XFlow——面向可靠多智能体工作流的可执行协议编程系统，以及其领域专用协议编程语言XPF（XFlow协议格式）。XFlow介于纯提示编排与标记式工作流描述之间。XPF保持可读的文字协议形式，同时可被编译并作为程序执行。其设计将非形式化语义工作保留在智能体内部，而将选定承诺迁移至可检查、可保留、可强制执行的硬结构。运行时，XFlow通过生命周期管控符号（lifycle-governed symbols）分阶段处理不确定性，这类符号是带验证与提交状态的类型化状态单元。智能体输出在成为共享状态前需经中介处理，而非通过提示、转录或隐式记忆传播。实验涵盖约束交互、长上下文推理与智能体软件工程领域，结果表明XFlow通过使约束、证据处理与过程需求显式化且可执行，提升了系统可靠性。