Metraipolis › archive › dc_45f7df7ee343

Credo: Reusable Declarative Primitives for Agentic Workflows — arXiv:2608.27790

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27790
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:11.377Z
SHA-256 of the archived text
ea72fb66ec5daef64aef1aee76403c93dfd4aaa5d2829ba7cbb6aedcfe58526b
Stable URL of this page
https://metraipolis.com/documento/dc_45f7df7ee343

How to cite

Credo: Reusable Declarative Primitives for Agentic Workflows — arXiv:2608.27790 — arXiv (en), https://arxiv.org/abs/2608.27790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45f7df7ee343 (Metraipolis archive dc_45f7df7ee343, sha256 ea72fb66ec5daef64aef1aee76403c93dfd4aaa5d2829ba7cbb6aedcfe58526b)
BibTeX
@misc{dc45f7df7ee343,
  title = {Credo: Reusable Declarative Primitives for Agentic Workflows — arXiv:2608.27790},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27790},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45f7df7ee343; sha256 ea72fb66ec5daef64aef1aee76403c93dfd4aaa5d2829ba7cbb6aedcfe58526b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An LLM application depends on both a model and a harness: the program that determines what each call sees, how many calls to make, and which answers to trust. Coding agents can now discover strong harnesses by searching over candidate programs, but the resulting artifact is an opaque block of imperative code whose logical steps, runtime signals, physical execution decisions, and prompt strategies remain implicit and task-specific, forcing subsequent tasks to start the harness search process from scratch. The potential for reuse, however, is substantial. A searched harness encodes significant knowledge, such as the logical steps that work, the signals that matter, the physical operator decisions that adapt execution, and the prompt strategies that are effective, yet this knowledge is buried in imperative code with no inspectable or reusable structure, nor does it carry any provenance or metadata. Credo addresses this problem by recovering a structured declarative description of a searched harness, tagging each extracted primitive with relevant metadata, and cataloguing all of it with provenance. A compiler can then bind stored primitives to generate harnesses for new tasks without having to start the search over from scratch. This paper provides preliminary results demonstrating the potential of our approach and lays out a related research agenda that the database community is well-positioned to tackle, including cost-based compilation over declarative catalogs and catalog maintenance under model and workload drift.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.27790 — 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 2026-10-17T10:33:42.346Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).