4 papers
REVES: REvision and VErification--Augmented Training for Test-Time Scaling
Yuanxin Liu, Ruida Zhou, Xinyan Zhao +6
Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning. However, standard post-training methods primarily o…
Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation
Yishuo Cai, Jiahui Liu, Yuanxin Liu +9
''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can ac…
HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents
Jiangweizhi Peng, Yuanxin Liu, Ruida Zhou +4
Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execut…
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
Han Zhong, Yutong Yin, Shenao Zhang +10
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, yet generating reliable reasoning processes remains a significant challenge. We p…