Metraipolis › archive › dc_5f05089340b2

WAR-CRAFT: Refining Web API Recommendations through Requirement Auditing — arXiv:2611.00564

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00564
License (as archived): CC0-1.0
Archived: 2026-11-03T10:41:57.439Z
SHA-256 of the archived text: 3cf98ba06554e693c02bd3dcc8d73f1b880641b74fa7591996f06bc4c5f64a0d
Stable URL of this page: https://metraipolis.com/documento/dc_5f05089340b2

How to cite

WAR-CRAFT: Refining Web API Recommendations through Requirement Auditing — arXiv:2611.00564 — arXiv (en), https://arxiv.org/abs/2611.00564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5f05089340b2 (Metraipolis archive dc_5f05089340b2, sha256 3cf98ba06554e693c02bd3dcc8d73f1b880641b74fa7591996f06bc4c5f64a0d)

BibTeX

@misc{dc5f05089340b2,
  title = {WAR-CRAFT: Refining Web API Recommendations through Requirement Auditing — arXiv:2611.00564},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00564},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5f05089340b2; sha256 3cf98ba06554e693c02bd3dcc8d73f1b880641b74fa7591996f06bc4c5f64a0d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Web API recommenders return a set of APIs for a mashup request but do not check it against provider documentation, the main public evidence of an API's capabilities. The set can therefore contain unsupported or redundant APIs and miss requested capabilities. Filling every apparent gap does not fix this, because a gap may already be served, may not need its own API, or may have no documented provider. We study post-recommendation refinement, which revises a frozen recommender's output using only the request, the catalog, and provider documentation. We propose WAR-CRAFT, which treats refinement as three decisions. An LLM removes unsupported or subsumed APIs by judging candidates jointly, then audits the remaining set against a requirement checklist derived from the request. For each uncovered requirement, a fine-tuned catalog-constrained Resolver proposes a catalog API or abstains, and an independent documentation check admits only supported proposals. On ProgrammableWeb with 7 heterogeneous upstream recommenders, WAR-CRAFT raises mean SetF1 from 0.558 to 0.644, above the strongest of 5 refinement baselines (62.5%), and roughly halves functional redundancy (0.127 to 0.065) without changing mean functional coverage. Gains range from +2.2 points on generative recommenders to +18.2 on fixed-cutoff rankers. At matched set sizes, WAR-CRAFT still outperforms truncating the upstream output, so the gain is not explained by set-size calibration alone. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00564 — 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 2026-11-03T10:39:50.177Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).