arXiv:2508. 09883v2 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving.
By Xiaojun Wu, Xiaoguang Jiang, Huiyang Li, Jucai Zhai, Dengfeng Liu, Qiaobo Hao, Huang Liu, Zhiguo Yang, Ji Xie, Ninglun Gu, Jin Yang, Kailai Zhang, Yelun Bao, Jun Wang
arXiv:2608.29623v1 Announce Type: cross
Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning...
By Yangsong Lan, Renkai Hu, HongKai Zheng, Bo Zhang, Renzhi Wang, Hongliang Dai, Piji Li
The paper investigates data efficiency and selection in On‑Policy Distillation (OPD) for large language models. It shows that 1‑shot OPD—training on a single example—consistently improves performance, especially when the example is hard, and that longer chain‑of‑thought (CoT) paths drive the gains rather than token entropy. Based on these findings, the authors propose a simple hard‑example selection strategy that, using only eight carefully chosen hard examples, matches the performance of a 17,000‑example baseline across models from 1.5B to 7B parameters.
By Zhinan Hou, Jiaqi Zhang, Xunliang Cai, Keyou You
arXiv:2509. 25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over the static problem set, wasting rollout budget on solved or overly difficult problems.
By Shijie Zhang, Zheng Xiao, Shiyu Liu, Guohao Sun, Kevin Zhang, Xiang Guo, Rujun Guo, Shaoyu Liu, Wangxiao Zhao, Guanjun Jiang
The paper introduces masked self‑distillation, a post‑training framework that trains a language model to internalize portions of its own intermediate reasoning traces. By varying the fraction of trace internalized, the authors demonstrate that models can achieve higher inference efficiency and improved task performance on math and graph‑coloring problems. Experiments on Qwen3‑4B and Qwen3‑8B show that the method generalizes well to in‑domain out‑of‑distribution cases without catastrophic forgetting, and that supervised fine‑tuning alone can reduce trace length at the expense of generalization.
By Durgesh Kalwar, Vardhan Palod, Jaya Adithya Pavuluri, Subbarao Kambhampati
The paper introduces an uncertainty-guided progressive contraction framework to reduce the amount of reasoning supervision needed for large language models. By building Monte Carlo reasoning trees around intermediate states, the method contracts the training corpus into a compact teacher-informed pool and then performs learner-aware contraction during supervised fine-tuning. Experiments show that the approach can use as little as 0.22% of the optimization budget of full-data SFT while maintaining or improving reasoning performance across diverse benchmarks and model families.
By Suorong Yang, Jiaxin Wang, Jiaming Su, Chentao Yue, Furao Shen, Peng Ye, Soujanya Poria