让复杂对话中的多个目标能中断后恢复，保持连续性。
From Task-Guided Conversational Graphs to Goal-Oriented Dialogue Runtimes
- 将目标、状态等抽象为运行时对象，实现跨任务连续性
- 支持目标暂停、修改、失效与恢复，不依赖聊天历史或身份
- 适合多领域、可中断的复杂对话系统设计
图结构和多智能体编排框架使大规模语言模型工作流在生产中成为可能，但无法解决用户拥有多个相互依赖目标时的对话连续性问题。本文聚焦于该设计空间的高复杂度场景，即目标可因其他目标的动作而被暂停、恢复、修改或作废。提出目标导向对话运行时（GODR），一种与框架无关的设计模式，将目标、任务框架、生命周期状态、失效规则和恢复契约作为一等运行时对象，同时将有限执行委托给图运行时、智能体、工具或API。GODR并非用于简单引导流程的替代方案，而是面向复杂、跨领域、可中断对话，其中仅靠智能体身份、聊天历史或执行图位置无法可靠恢复目标连续性。论文形式化了该问题，提出了运行时对象与架构选择标准，并将评估定位为未来实证验证的议程，而非性能指标声明。
原文摘要 · Abstract (English)
Graph and multi-agent orchestration frameworks make production large language model (LLM) workflows practical, but they do not by themselves solve conversational continuity when users maintain several interdependent objectives. This conceptual systems paper focuses on the high-complexity end of that design space, where goals can be suspended, resumed, revised, and invalidated by actions in other goals. We introduce the Goal-Oriented Dialogue Runtime (GODR), a framework-neutral design pattern that treats goals, task frames, lifecycle state, invalidation rules, and resumption contracts as first-class runtime objects while delegating bounded execution to graph runtimes, agents, tools, or application programming interfaces (APIs). GODR is not proposed as a replacement for workflow graphs in simple guided processes; it is intended for complex, multi-domain, interruptible conversations where objective continuity cannot be recovered reliably from agent identity, chat history, or execution-graph position alone. The paper formalizes the problem, proposes runtime objects and architecture-selection criteria, and frames evaluation as an agenda for future empirical validation rather than as a measured performance claim.
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。