为流数据中的智能体设计可分叉的共享日志，解决性能干扰与安全写入问题。
AgileLog: A Forkable Shared Log for Agents on Data Streams
- 提出可分叉的共享日志抽象，支持智能体在流数据上安全运行。
- 实现低成本分叉与逻辑/性能隔离，显著降低智能体任务干扰。
- 适合构建高并发、低延迟的流式智能体系统，如实时决策场景。
在现代数据流系统中，除了传统程序外，新型实体——人工智能智能体正涌现，它们利用大模型推理，在自然语言描述的任务下处理流数据。然而，现有流系统无法充分支持智能体：缺乏避免智能体任务导致的性能干扰机制，也难以安全处理智能体写入。本文认为，作为流数据核心抽象的共享日志必须支持自身分叉，而这种可分叉共享日志可成为智能体操作流数据的理想基础。为此，我们提出 AgileLog，一种面向智能体用例的新共享日志抽象，引入创新的分叉原语。我们设计了 Bolt，其基于新方法实现廉价分叉，并提供逻辑与性能隔离，有效保障系统稳定性和响应性。
原文摘要 · Abstract (English)
In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI agents. Unlike traditional programs, AI agents use LLM reasoning to accomplish high-level tasks specified in natural language over streaming data. Unfortunately, current streaming systems cannot fully support agents: they lack the fundamental mechanisms to avoid the performance interference caused by agentic tasks and to safely handle agentic writes. We argue that the shared log, the core abstraction underlying streaming data, must support creating forks of itself, and that such a forkable shared log serves as a great substrate for agents acting on streaming data. We propose AgileLog, a new shared log abstraction that provides novel forking primitives for agentic use cases. We design Bolt, an implementation of the AgileLog abstraction, that uses novel techniques to make forks cheap, and provide logical and performance isolation.
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。