Metraipolis › archive › dc_ecf8e29622db

Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows — arXiv:2610.05815

Source
arXiv
Original
https://arxiv.org/abs/2610.05815
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:25.333Z
SHA-256 of the archived text
d65dbe95e1c519fdfe5039193a798338a40099d61d4ec0cdf773ef8997ff8b9f
Stable URL of this page
https://metraipolis.com/documento/dc_ecf8e29622db

How to cite

Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows — arXiv:2610.05815 — arXiv, https://arxiv.org/abs/2610.05815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecf8e29622db (Metraipolis archive dc_ecf8e29622db, sha256 d65dbe95e1c519fdfe5039193a798338a40099d61d4ec0cdf773ef8997ff8b9f)
BibTeX
@misc{dcecf8e29622db,
  title = {Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows — arXiv:2610.05815},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecf8e29622db; sha256 d65dbe95e1c519fdfe5039193a798338a40099d61d4ec0cdf773ef8997ff8b9f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Continuous language flows generate text by denoising all positions of a target canvas together. The natural way to add reasoning to such a model is to write a trace ahead of the answer, but the trace length changes from question to question. The answer start is therefore unknown during denoising, and the model has to decide the trace length, the place of every trace token, and the answer at the same time. We propose Plan Canvas to fix the boundary between the trace and the answer. A plan region of fixed capacity holds a compact trace, supervised padding fills its unused positions, and the answer starts at a fixed position. The fixed regions also allow separate denoising clocks for the plan and for the answer. With the trace text, backbone, and canvas length of the free-trace baseline held fixed, Plan Canvas improves accuracy on ProsQA and on Deep ProsQA, a graph benchmark with longer proofs. On Deep ProsQA, accuracy rises from 73.0\% to 87.0\%, the share of questions answered with a valid path rises from 30.8\% to 59.1\%, and the gain is largest on the longest proofs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.05815 — 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 2026-10-06T05:24:20.347Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).