On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models. However, when the expert fails on harder problems, existing trajectory-guided methods lose their main source of supervision, and these failed trajectories are typically discarded as negative samples.
arXiv:2603. 09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.
By Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su, Hongru Hou, Hengrui Chen, Ao Xu, Deqing Yang
arXiv:2606. 07006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior.
By Yongliang Miao, Fengyuan Liu, Wei Shi, Yanguang Liu, Fei Sun, Na Zou, Mengnan Du
arXiv:2605. 28742v2 Announce Type: replace Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks.
By Linas Nasvytis, Simon Jerome Han, Ben Prystawski, Satchel Grant, Noah D. Goodman, Judith E. Fan
arXiv:2608. 05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them.
By Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Deguo Xia, Jizhou Huang
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
By Kyuyoung Kim, Kevin Wang, Yunfei Xie, Peiyang Xu, Peiyao Sheng, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
By Vaggelis Dorovatas, Nancy Kalaj, Rahaf Aljundi
arXiv:2607. 28638v1 Announce Type: cross Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights.
By Yan Song, Xidong Feng, Bo Liu, Xinyu Cui, Haotian Fu, Zichen Liu, Mengyue Yang, Cheng Deng, Jian Zhao, Jun Wang
arXiv:2607. 16205v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts.
By Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Liwei Qian, Xin Pei, Jizhou Huang
arXiv:2604. 22565v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts.
By Shaoang Li, Yanhang Shi, Yufei Li, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Jian Li
arXiv:2511. 21667v4 Announce Type: replace Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers.
By Locke Cai, Max Ryabinin, Ivan Provilkov
arXiv:2509. 21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up.
By Woosung Koh, Juyoung Suk, Sungjun Han, Se-Young Yun, Jamin Shin