arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.19409cs.SEcs.PL
收藏

OpenRath: 面向会话的代理系统运行时状态

OpenRath: Session-Centered Runtime State for Agent Systems

Fukang Wen, Zhijie Wang, Ruilin Xu

AI总结:

针对代理系统运行时状态碎片化问题,提出以Session为核心的一等运行时抽象,支持分支、检查、重放、后端感知和组合,使fork、merge和replay成为显式运行时操作。

摘要:

现代代理系统常常遭受碎片化的运行时状态:对话记录、工具效果、内存事件、工作区放置、分支来源和重放证据被分别记录,难以检查或重现。OpenRath通过一个类似PyTorch的编程模型来解决这个问题,适用于多代理、多会话系统。这里的类比涉及中心一等运行时抽象的角色,而非张量计算。其核心抽象是Session,即在代理和工作流之间传递的运行时值。Session是可分支、可检查、可重放、后端感知且可组合的。它记录对话片段、沙箱放置、谱系元数据、令牌使用、待处理工作和工具证据,同时定义内存交互进入运行时记录的位置。由于此状态由程序执行中使用的同一值携带,fork、merge和replay成为显式的运行时操作,而非从外部痕迹重建的状态。OpenRath进一步定义了Sandbox、Tool、Agent、Memory、Workflow和Selector,其中Selector将控制流转化为运行时路由的决策。本报告介绍了编程模型、架构、审计里程碑和证据协议。其主张仅限于受控的运行时属性,而广泛的定量比较、实时提供者质量、可选后端可用性和内存质量留待后续评估。核心论点是Session为代理系统提供了一个一等运行时值,用于可审计的组合。

英文摘要:

Modern agent systems often suffer from fragmented runtime state: transcripts, tool effects, memory events, workspace placement, branch provenance, and replay evidence are recorded separately and become difficult to inspect or reproduce. OpenRath addresses this issue with a PyTorch-like programming model for multi-agent, multi-session systems. The analogy concerns the role of a central first-class runtime abstraction, not tensor computation. Its core abstraction is Session, the runtime value passed between agents and workflows. A Session is branchable, inspectable, replayable, backend-aware, and composable. It records conversation chunks, sandbox placement, lineage metadata, token usage, pending work, and tool evidence, while defining where memory interactions enter the runtime record. Since this state is carried by the same value used in program execution, fork, merge, and replay become explicit runtime operations rather than states reconstructed from external traces. OpenRath further defines Sandbox, Tool, Agent, Memory, Workflow, and Selector, with Selector turning control flow into runtime-routed decisions. This report presents the programming model, architecture, audited milestones, and evidence protocol. Its claims are limited to controlled runtime properties, while broad quantitative comparisons, live-provider quality, optional-backend availability, and memory quality are left for follow-on evaluation. The central thesis is that Session provides agent systems with a first-class runtime value for auditable composition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑