most citedRedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

1 citations · 1 across the 21 of their papers we have counts for

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training

Nan Qiao, Yebin Yang, Weinong Wang +10

Reinforcement mid-training lets language models learn internal thoughts from unlabeled text, but efficient token-level credit assignment remains challenging. Existing group-relativ…

cs.AI2025

Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving

Xinji Mai, Haotian Xu, Zhong-Zhi Li +5

Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based reward…