Metraipolis › archive › dc_3a52379ea73b

Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution — arXiv:2608.21341

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21341
License (as archived)
CC0-1.0
Archived
2026-10-18T10:34:31.034Z
SHA-256 of the archived text
6ed2297e73bf00c986baec95b3984e6a5a35d9d39834879c22e5d19d8765a9b6
Stable URL of this page
https://metraipolis.com/documento/dc_3a52379ea73b

How to cite

Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution — arXiv:2608.21341 — arXiv (en), https://arxiv.org/abs/2608.21341 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a52379ea73b (Metraipolis archive dc_3a52379ea73b, sha256 6ed2297e73bf00c986baec95b3984e6a5a35d9d39834879c22e5d19d8765a9b6)
BibTeX
@misc{dc3a52379ea73b,
  title = {Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution — arXiv:2608.21341},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21341},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a52379ea73b; sha256 6ed2297e73bf00c986baec95b3984e6a5a35d9d39834879c22e5d19d8765a9b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21341. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-24 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.21341 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:28:20.992Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).