Metraipolis › archive › dc_be0d0cf3cbe3

DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds — arXiv:2608.06113

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06113
License (as archived)
CC0-1.0
Archived
2026-10-27T08:04:43.095Z
SHA-256 of the archived text
69d087d08de39987d61737a6fe21c8b6ee7233e9b6695401cf56a52db9cd3edf
Stable URL of this page
https://metraipolis.com/documento/dc_be0d0cf3cbe3

How to cite

DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds — arXiv:2608.06113 — arXiv (en), https://arxiv.org/abs/2608.06113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be0d0cf3cbe3 (Metraipolis archive dc_be0d0cf3cbe3, sha256 69d087d08de39987d61737a6fe21c8b6ee7233e9b6695401cf56a52db9cd3edf)
BibTeX
@misc{dcbe0d0cf3cbe3,
  title = {DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds — arXiv:2608.06113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be0d0cf3cbe3; sha256 69d087d08de39987d61737a6fe21c8b6ee7233e9b6695401cf56a52db9cd3edf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

CLI-based software-engineering agents have matured rapidly, yet the open ecosystem has converged on a single training environment: trajectory datasets used to fine-tune open models are collected almost exclusively under OpenHands. Models fine-tuned on this data score well under OpenHands but degrade substantially when deployed under any non-training scaffold. Untrained base models do not show this divergence, indicating the gap is fine-tuning-induced and tied to the conventions of the training scaffold. We argue that a load-bearing scaffold-specific behavior is planning structure, in two senses this paper distinguishes: explicit planning, a pre-execution plan produced as a first-class artifact, and implicit planning, the structural conventions that shape execution throughout the agent loop. Under this hypothesis, closing the gap requires moving planning from a fixed scaffold artifact to a learned model capability. We introduce Decoupling CLI Agent Scaffolding (DCAS), a backend-substitution interception layer that routes API traffic between any CLI scaffold and any backend model without modifying the scaffold, enabling cross-scaffold evaluation and planning-aware trajectory collection. Using DCAS, a controlled plan-source intervention confirms planning quality is a high-leverage component, with gains exceeding the cross-scaffold drops we observe. A model fine-tuned on a small set of DCAS-collected planning-aware trajectories under a single scaffold gains consistently across non-training scaffolds, and the two senses of planning are empirically separable in training data.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-07 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.06113 — 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 2026-10-27T07:55:47.050Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).