软件工程与编程智能体 颠覆级 有讲解视频
发表时间
2026-08-21
arXiv
2608.21341

收录解读

自然语言工作流为智能体提供了类似软件的接口,但现有方法因数据依赖隐式、长指令执行失败等问题而不可靠。

本文提出Artic,一种工件驱动的工作流编译器,将自然语言工作流转化为显式声明读写工件、约束和控制的表示,并通过约束优化识别并细化困难步骤。

在11个真实领域工作流的488个问题实例上,Artic将任务解决率提升28个百分点,跨模型和重复执行一致性分别提升32和56个百分点。

该方法为智能体可靠执行提供了可复用的编译框架,但仅在自然语言工作流场景验证,未覆盖更广泛的智能体系统。

原始摘要

Natural-language workflows offer a software-like interface for agents: domain experts can write reusable procedures, and agents can execute them as instructions. This promise is not yet reliable. Workflow descriptions often leave data dependencies implicit, so the executor must infer which prior results a step should use; agents can also fail to follow long or branching instructions under context pressure. We propose Artic, an artifact-driven workflow compiler that transforms a natural-language workflow into an artifact-driven workflow in which each step declares the artifacts it reads and writes, constraints gate produced artifacts, and explicit control transfers route execution. This representation exposes the enforcement burden placed on agent execution, allowing the compiler to identify steps that depend on too much state or contain difficult control logic and refine them through constrained optimization. To validate the LLM-assisted transformation, Artic decomposes faithfulness checking into local obligations and uses scenario-based dry runs to test whether compiled workflow regions conform to the source workflow. We evaluate Artic on 488 problem instances from 11 real-world domain workflows; it improves task resolve rate by 28 percentage points over the original text workflow. We also show that workflows compiled by Artic are 32 and 56 percentage points more consistent in cross-model and repeated-execution setups, respectively.

解读视频

相关论文

链接