智能体事务：迈向ACID合规的智能体系统

摘要

大语言模型（LLM）智能体正从对话式助手演化为自主系统，能够通过推理、工具使用、代码生成和工作空间操作来执行长时程任务。随着智能体日益在持久化环境和多步工作流中运行，它们面临着与事务性数据库系统所解决的挑战相类似的问题：可靠执行、结果一致性、安全并发以及持久化状态管理。我们引入智能体事务的概念，并提出一个符合ACID规范的智能体系统框架，通过四种语义保障重新诠释经典ACID属性在智能体执行中的含义：语义原子性、语义一致性、语义隔离性和语义持久性。这些属性共同为在模型不确定性和动态执行环境下构建可靠智能体系统提供了原则性基础。为实例化该框架，我们开发了一个符合ACID规范的数据智能体，通过事务性探索-执行-验证循环、事务性技能中心、基于分歧置信度的验证、语义依赖感知的隔离以及事务感知的语义状态管理来实现上述保障。在广泛使用的基准测试上的实验结果表明，我们的系统相较于包括Claude Code在内的最先进智能体实现了10.6%的性能提升。本工作开启了将事务性原则和系统架构扩展至构建可信、可扩展且自我进化的AI智能体系统的更广泛研究议程。

English

Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasoning, tool use, code generation, and workspace manipulation. As agents increasingly operate over persistent environments and multi-step workflows, they face challenges analogous to those addressed by transactional database systems: reliable execution, consistent outcomes, safe concurrency, and durable state management. We introduce the concept of an agentic transaction and propose an ACID-compliant agent system framework that reinterprets the classical ACID properties for agent execution through four semantic guarantees: Semantic Atomicity, Semantic Consistency, Semantic Isolation, and Semantic Durability. Together, these properties provide a principled foundation for building reliable agent systems despite model uncertainty and dynamic execution environments. To instantiate this framework, we develop an ACID-compliant data agent that realizes these guarantees through transactional exploration-execution-validation cycles, transactional skill hubs, confidence divergence-based validation, semantic dependency-aware isolation, and transaction-aware semantic state management. Experimental results on widely used benchmarks show that our system achieves a 10.6% improvement over state-of-the-art agents, including Claude Code. This work opens a broader research agenda on extending transactional principles and system architectures toward building trustworthy, scalable, and self-evolving AI agent systems.