22 papers
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Rui Wang, Hongru Wang, Yi Chen +4
The paper investigates how on-policy distillation guides large language model students during training, identifies two main failure modes—student‑teacher mismatch and length exploi…
Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
Rui Liu, Dian Yu, Tong Zheng +8
Reinforcement learning with verifiable rewards (RLVR) has advanced reasoning capabilities in multimodal large language models. However, existing methods typically treat visual inpu…
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Yucheng Shi, Zhenwen Liang, Kishan Panaganti +3
We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In z…
Self-Rewarding Vision-Language Model via Reasoning Decomposition
Zongxia Li, Wenhao Yu, Chengsong Huang +8
Vision-Language Models (VLMs) often suffer from visual hallucinations: generating things that are not consistent with visual inputs and language shortcuts, where they skip the visu…
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Yujun Zhou, Zhenwen Liang, Haolin Liu +7
Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve wit…
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Chengsong Huang, Wenhao Yu, Xiaoyang Wang +6
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, e…