Metraipolis › archive › dc_3cac866fa8aa

RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty — arXiv:2610.11352

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11352
License (as archived)
CC0-1.0
Archived
2026-10-09T05:47:39.598Z
SHA-256 of the archived text
8bd34eb3825d6adb668a7acc9075229811ef03ae5119767e9e96d4c381ec68d4
Stable URL of this page
https://metraipolis.com/documento/dc_3cac866fa8aa

How to cite

RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty — arXiv:2610.11352 — arXiv (en), https://arxiv.org/abs/2610.11352 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3cac866fa8aa (Metraipolis archive dc_3cac866fa8aa, sha256 8bd34eb3825d6adb668a7acc9075229811ef03ae5119767e9e96d4c381ec68d4)
BibTeX
@misc{dc3cac866fa8aa,
  title = {RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty — arXiv:2610.11352},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11352},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3cac866fa8aa; sha256 8bd34eb3825d6adb668a7acc9075229811ef03ae5119767e9e96d4c381ec68d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11352. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities. However, since RLVR does not explicitly account for calibration during training, it can lead to severe calibration degradation, including overconfidence. Recent calibration-aware training methods for LMs, which incorporate objectives for uncertainty estimation into training, improve calibration but still exhibit overconfidence under distribution shift, while sacrificing reasoning performance. To this end, we propose RL-ARC, a calibration-aware training framework that jointly leverages reasoning confidence and answer confidence. Specifically, RL-ARC leverages reasoning confidence as an auxiliary signal for calibrating answer confidence, applying it as reasoning-guided regularization for correct cases and as an overconfidence penalty for incorrect cases. Comprehensive results across ID and OOD settings show that, beyond improving calibration, RL-ARC enables reasoning models to adaptively estimate confidence based on the given question without substantially sacrificing reasoning performance, thereby highlighting the importance of reasoning confidence for training reliable reasoning models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.11352 — 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 2026-10-09T05:47:00.692Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).