The paper introduces the Posterior Concentration Phenomenon (PCP), a length‑dependent failure mode where probability‑based rewards collapse to a narrow interval for long reasoning traces, destabilizing verifier‑free reinforcement learning. To address this, the authors propose RLCPR, a framework that uses uncertainty‑aware data sampling and concentration‑aware regularization to mitigate PCP, improving token efficiency and outperforming state‑of‑the‑art baselines on multiple reasoning benchmarks.
By Shiu-Hong Kao, Yubo Zhao, Zhenyu Tian, Pengzhan Sun, Yicong Li, Angela Yao
arXiv:2605. 24396v2 Announce Type: replace Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute.
By Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu, J. Zico Kolter, Andrej Risteski, Aditi Raghunathan
arXiv:2512.13095v3 Announce Type: replace
Abstract: To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into...
By Feng Zhang, Zezhong Tan, Xinhong Ma, Ziqiang Dong, Xi Leng, Jianfei Zhao, Xin Sun, Yang Yang, Guanjun Jiang
arXiv:2604. 09482v2 Announce Type: replace Abstract: Reasoning in knowledge-intensive domains remains challenging as intermediate steps are often not locally verifiable: unlike math or code, evaluating step correctness may require synthesizing clues across large external knowledge sources.
By Jiwoong Sohn, Tomasz Sternal, Kenneth Styppa, Torsten Hoefler, Michael Moor
arXiv:2607. 22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens.
By Vatsal Baherwani, Tom Goldstein, Ashwinee Panda
arXiv:2410.23912v3 Announce Type: replace-cross
Abstract: The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex...
By Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih, Yi Hsuan Tseng, Pei-Yuan Wu
The paper demonstrates that fine‑tuning reasoning models to predict their own confidence at intermediate steps—using only 600 self‑supervised examples—substantially improves inference efficiency. Without adding any explicit stopping or length penalties, the models generate up to 25 % fewer tokens while maintaining accuracy on mathematical, scientific, and coding benchmarks across several architectures. The study finds that confidence supervision preserves the models’ high‑level reasoning structure rather than merely suppressing specific behaviors.
By Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe, Chenrui Fan, Sourya Basu, Genta Indra Winata, Anirban Das, Soheil Feizi, Nima Chitsazan
arXiv:2602. 07832v3 Announce Type: replace-cross Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking.
By Xian Wu, Kaijie Zhu, Ying Zhang, Lun Wang, Wenbo Guo
arXiv:2609.37119v1 Announce Type: cross
Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
By Hongyang Li, Xiao Li, Caesar Wu, Said Mammar, Gr\'egoire Danoy, Pascal Bouvry
arXiv:2608.28771v1 Announce Type: new
Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with...
By Xin Jiang, Minhao Wang, Wen Wu, Zhentao Xie, Shangheng Du, Jinxin Shi, Jiabao Zhao
arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.
By Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu
arXiv:2606. 17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model.
By Violet Xiang, Amrith Setlur, Chase Blagden, Nick Haber, Aviral Kumar