作者位次 #3/6ACL 2026Poster· Natural Language Processing
The Retrieval Bottleneck: Scaling Laws for Reinforcement Learning in RAG
Shu Zhou · Jinman Leng · Yufei Song · Xin Wang · Tao Fan · Hao Wang
摘要
Scaling laws have enabled predictable compute allocation for pre-training and for RL in reasoning tasks. However, research on retrieval reinforcement generation (RAG) remains insufficient and there is a lack of fundamental understanding of the interaction between retrieval quality and reinforceme...