arXiv:2607. 01511v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models.
By Hongyang He, Jiuming Liu, Victor Sanchez
arXiv:2607. 16972v1 Announce Type: new Abstract: Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations.
By Varun Yerram, He He, Eunsol Choi
arXiv:2607.26621v3 Announce Type: replace-cross
Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their use as the backbone of foundation recommendati...
By Hao Jiang, Peiru Du, Pengfei Yao, Mengting Li, Siyuan Lou, Kuo Cai, Sheng Yu, Qiang Luo, Jian Liang, Ruiming Tang, Fei Pan, Peng Jiang, Wenwu Ou
arXiv:2608.23256v1 Announce Type: new
Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reason...
By Yinhao Tang, Youqing Fang, Yanan Sun, Jiangning Liu, Ziyi Wang, Xun Zhao, Weiming Zhang, Bin Liu, Kuikun Liu, Wenwei Zhang, Kai Chen
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.
The paper investigates whether the high costs of training chain-of-thought reasoning models can be reduced through algorithmic design. It introduces an autocurriculum approach that lets the model select which problems to focus on during training, showing that this method provably improves both supervised fine‑tuning and reinforcement learning. For supervised fine‑tuning, autocurriculum requires exponentially fewer reasoning demonstrations by targeting prompts where the model struggles, while for reinforcement learning it decouples computational cost from the quality of the reference model, making the burn‑in cost nearly independent of target accuracy.
By Nived Rajaraman, Audrey Huang, Miro Dudik, Robert Schapire, Dylan J. Foster, Akshay Krishnamurthy