Metraipolis › archive › dc_6825fc6f41eb

How Does Chain-of-Thought Supervision Teach Models to Reason? A Theoretical Analysis — arXiv:2611.01740

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01740
License (as archived)
CC0-1.0
Archived
2026-11-03T11:21:13.757Z
SHA-256 of the archived text
c6b56a4c7578b9c0a84f815c343f4fedb4e075ce92e116603800956c57e5e744
Stable URL of this page
https://metraipolis.com/documento/dc_6825fc6f41eb

How to cite

How Does Chain-of-Thought Supervision Teach Models to Reason? A Theoretical Analysis — arXiv:2611.01740 — arXiv (en), https://arxiv.org/abs/2611.01740 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6825fc6f41eb (Metraipolis archive dc_6825fc6f41eb, sha256 c6b56a4c7578b9c0a84f815c343f4fedb4e075ce92e116603800956c57e5e744)
BibTeX
@misc{dc6825fc6f41eb,
  title = {How Does Chain-of-Thought Supervision Teach Models to Reason? A Theoretical Analysis — arXiv:2611.01740},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01740},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6825fc6f41eb; sha256 c6b56a4c7578b9c0a84f815c343f4fedb4e075ce92e116603800956c57e5e744},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01740. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Training with chain-of-thought (CoT) supervision is an effective approach for teaching models multi-step reasoning procedures. At inference time, however, models may need to continue reasoning beyond the finite teacher CoT sequences observed during training, and longer reasoning can instead degrade performance, a phenomenon known as overthinking. How the amount and structure of training-time CoT give rise to such failures remains theoretically poorly understood. To study this problem, we introduce an in-context weight prediction model trained on finite gradient descent trajectories for linear regression. Using high-dimensional asymptotic analysis, we show that the success and failure modes of long-horizon reasoning undergo phase transitions depending on the context length and the total amount of training CoT. We further distinguish two mechanisms of overthinking, error accumulation and error amplification, and show that with short training contexts, increasing the training CoT budget can worsen long-horizon error before eventually stabilizing reasoning. Experiments with fully trained linear and multi-head softmax attention further show that these qualitative behaviors persist. Our results provide a theoretical account linking properties of training-time CoT to inference-time failures and offer guidance for designing teacher CoT that supports stable reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.01740 — 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 2026-11-03T11:02:37.555Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).