2 papers
cs.LG2026
The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
Zibo Zhao, Yuanting Zha, Haipeng Zhang +1
Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how…
cs.LG2025
Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks
Xingcheng Xu, Zibo Zhao, Haipeng Zhang +1
Transformer-based models excel in various tasks but their generalization capabilities, especially in arithmetic reasoning, remain incompletely understood. Arithmetic tasks provide…