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

arXiv: https://arxiv.org/abs/2608.21341 · HTML: https://mlsanity.com/paper/2608.21341/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 41 of its 64 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 41)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models](https://mlsanity.com/paper/2310.20410/) (2023)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [TrustAgent: Towards Safe and Trustworthy LLM-based Agents](https://mlsanity.com/paper/2402.01586/) (2024)
- [nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models](https://mlsanity.com/paper/2303.04864/) (2023)
- [FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents](https://mlsanity.com/paper/2406.14884/) (2024)
- [SkillGen: Verified Inference-Time Agent Skill Synthesis](https://mlsanity.com/paper/2605.10999/) (2026)
- [When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail](https://mlsanity.com/paper/2601.04748/) (2026)
- [Enforcing Temporal Constraints for LLM Agents](https://mlsanity.com/paper/2512.23738/) (2025)
- [LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios](https://mlsanity.com/paper/2411.07037/) (2024)
- [WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models](https://mlsanity.com/paper/2411.05451/) (2024)
- [SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?](https://mlsanity.com/paper/2603.00718/) (2026)
- [SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents](https://mlsanity.com/paper/2506.08119/) (2025)
- [Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts](https://mlsanity.com/paper/2409.12447/) (2024)
- [FlowAgent: Achieving Compliance and Flexibility for Workflow Agents](https://mlsanity.com/paper/2502.14345/) (2025)
- [TAI3: Testing Agent Integrity in Interpreting User Intent](https://mlsanity.com/paper/2506.07524/) (2025)
- [AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios](https://mlsanity.com/paper/2601.20613/) (2026)
- [SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents](https://mlsanity.com/paper/2605.03353/) (2026)
- [CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?](https://mlsanity.com/paper/2605.16679/) (2026)

## Abstract (arXiv)

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.