Chronos：面向有状态智能体应用的高效跨数据存储即插即用分支机制
Chronos: Efficient Bolt-on Branching Across Data Stores for Stateful Agentic Applications
- MIT CSAIL（麻省理工学院计算机科学和人工智能实验室）
- University of Arizona（亚利桑那大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对有状态智能体应用跨异构存储分支低效且易不一致的问题，提出即插即用系统Chronos，采用紧凑区间版本化与分支管理分离架构，实现快速分支与原子合并，MCTS探索提速达16.7倍。
AI中文摘要：
数据密集型应用日益采用推测执行来探索多个候选路径，其中每条路径都会修改分布在异构数据存储中的状态。这一趋势因工具调用智能体的兴起而加剧。因此，应用需要能够快速创建分支、隔离状态修改路径，并在各存储间一致地合并更改，同时不引入显著查询开销的数据系统。现有系统仅提供部分支持，迫使应用手动协调分支与合并，这增加了开销并带来跨存储状态不一致的风险。为解决此问题，我们提出Chronos，一个提供跨异构数据存储分支能力的即插即用系统。我们做出两项贡献。首先，Chronos引入一种紧凑的基于区间的版本化技术，通过简单的查询重写实现高效分支与数据共享。其次，Chronos引入一种即插即用架构，将每个存储内的分支管理与数据路径分离。结合基于区间的版本化，这种分离为合并提供原子性的跨存储可见性，并使Chronos能够支持多种数据存储而无需修改其引擎。我们为PostgreSQL、SQLite、DuckDB、Qdrant以及一个基于DBMS的文件系统实现了Chronos。我们使用跨存储智能体工作流、MCTS式探索以及各存储基准对其进行评估。Chronos运行MCTS式探索的速度比现有方法快达16.7倍，同时在各底层存储上保持实用的查询性能。在并发跨存储工作流下，Chronos防止部分可见的合并，同时大幅优于串行执行。
英文摘要：
Data-centric applications increasingly use speculative execution to explore multiple candidate paths where each path modifies state distributed across heterogeneous data stores. This trend is intensified by the rise of tool-calling agents. Hence, applications need data systems that can create branches quickly, isolate state-modifying paths, and merge changes consistently across stores without imposing substantial query overhead. Existing systems provide only partial support, forcing applications to coordinate branches and merges manually, which increases overhead and risks inconsistent cross-store state. To solve this problem, we introduce Chronos, a bolt-on system that provides branching capability across heterogeneous data stores. We make two contributions. First, Chronos introduces a compact interval-based versioning technique that enables efficient branching and data sharing through simple query rewrite. Second, Chronos introduces a bolt-on architecture that separates branch management from data path within each store. Combined with interval-based versioning, this separation provides atomic cross-store visibility for merges and enables Chronos to support diverse data stores without modifying their engines. We implement Chronos for PostgreSQL, SQLite, DuckDB, Qdrant, and a DBMS-backed filesystem. We evaluate it using cross-store agent workflows, MCTS-style exploration, and per-store benchmarks. Chronos runs MCTS-style exploration up to 16.7x faster than existing approaches while maintaining practical query performance across the underlying stores. Under concurrent cross-store workflows, Chronos prevents partially visible merges while substantially outperforming serialized execution.
