作者位次 #2/5ACL 2026Findings· Findings of ACL
SCALER : Synthetic Scalable Adaptive Learning Environment for Reasoning
Caijun Xu · Changyi Xiao · Zhongyuan Peng · Xinrun Wang · Yixin Cao
摘要
Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often slows when task difficulty becomes poorly aligned with mode...