arXiv:2608. 03972v1 Announce Type: new Abstract: 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.
By Jinhe Bi, Chennan Zhou, Zengjie Jin, Aniri, Shuo Lu, Wenke Huang, Hu Cao, Xun Xiao, Zhihong Zhu, Volker Tresp, Fei Shen, Yunpu Ma, Tat-Seng Chua
Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whet...
The paper introduces $R^3$, a post‑training method that converts vision‑language models into robotic reasoners by first mid‑training on expert reasoning traces and then refining them with single‑step rubric‑based reinforcement learning. $R^3$ enables free‑form language reasoning to guide low‑level manipulation policies, improving exploration, generalization, and performance on long‑horizon tasks in Language Table and simulated bimanual grocery packing benchmarks. The approach outperforms instruction‑only imitation learning baselines and demonstrates that natural language reasoning can serve as a test‑time compute mechanism for steering robotic actions.
By Lehong Wu, Yuxiao Qu, Zheyuan Hu, Ivan Zhang, Limin Wei, Zackory Erickson, Aviral Kumar
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:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
By Yixiu Mao, Yun Qu, Qi Wang, Heming Zou, Xiangyang Ji
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