Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution

2026-08-21

AI Summary

为解决自然语言工作流执行不可靠的问题，提出Artic编译器，将自然语言工作流转换为基于工件的工作流，提高任务解决率和一致性。

Abstract

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.

Problem

• Natural-language workflows
• data dependencies
• context pressure
• agent execution
• reliability

Innovation

• artifact-driven workflow
• natural-language workflows
• constraint-based optimization
• faithfulness checking
• scenario-based dry runs