AI 代理终于有了数据库级的可靠性
AI 代理在长时间任务里经常出错、互相干扰，就像没有事务管理的数据库。这篇论文把数据库的 ACID 原则搬到了 AI 代理上，但重新定义为语义原子性、一致性、隔离性和持久性——不是死板的操作级保证，而是语义层面的。他们做了一个数据代理，通过探索-执行-验证循环、技能中心、置信度分歧验证等机制，在多个基准上比 Claude Code 等最强代理提升了 10.6%。这不是你明天就能用的工具，但它指出了 AI 系统走向可靠的一个关键方向：像数据库一样，把不确定性管起来。
📄 原文摘要(英文)
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.