Metraipolis › archive › dc_07c50fa2e16c

CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models — arXiv:2610.20642

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20642
License (as archived)
CC0-1.0
Archived
2026-10-16T09:06:13.099Z
SHA-256 of the archived text
c5228fc2bf395c39f9089635443bd5cdd7a1a675b54242f90c341b2b93302794
Stable URL of this page
https://metraipolis.com/documento/dc_07c50fa2e16c

How to cite

CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models — arXiv:2610.20642 — arXiv (en), https://arxiv.org/abs/2610.20642 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07c50fa2e16c (Metraipolis archive dc_07c50fa2e16c, sha256 c5228fc2bf395c39f9089635443bd5cdd7a1a675b54242f90c341b2b93302794)
BibTeX
@misc{dc07c50fa2e16c,
  title = {CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models — arXiv:2610.20642},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20642},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07c50fa2e16c; sha256 c5228fc2bf395c39f9089635443bd5cdd7a1a675b54242f90c341b2b93302794},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20642. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent latent reasoning methods move beyond discrete Chain-of-Thought (CoT) by replacing sampled tokens with continuous soft embeddings or hidden states, enabling richer intermediate representations and preserving alternative reasoning paths. However, the need for latent reasoning varies across decoding steps: confident predictions favor discrete commitment, whereas ambiguous steps benefit from preserving multiple plausible alternatives. Existing approaches typically handle this variation through either global soft activation or hard switching based on uncertainty thresholds, treating latent intervention as an all-or-nothing decision rather than continuously adapting its strength. To address this limitation, we propose Competitive Token Selection (CoTS), a training-free framework that reframes latent intervention from binary mode selection into continuous allocation at the token level. CoTS uses the probability competition between the two most likely candidates to dynamically balance discrete commitment and soft exploration at each reasoning step. The second candidate represents the strongest alternative to the model's preferred continuation, so the separation between the two directly reflects the stability of the current discrete choice. When one candidate clearly dominates, CoTS keeps the representation close to the sampled discrete token to preserve a stable reasoning trajectory; as the competition strengthens, it increases the contribution of the soft representation to retain plausible alternatives. This competition-based allocation requires neither manually tuned switching thresholds nor mixing coefficients, and introduces no additional forward passes. Experiments across six reasoning benchmarks demonstrate that CoTS consistently outperforms standard CoT and state-of-the-art training-free latent reasoning methods. 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: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.20642 — 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 2026-10-16T08:44:17.854Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).