一作ACL 2026Poster· Natural Language Processing
RAG -on-a-Diet: A Reinforcement Learning-Based Dynamic Resource Optimization Framework for RAG
Hongwen Ding · Yizheng Zhao
摘要
Retrieval-Augmented Generation (RAG) has become the backbone of knowledge-intensive multi-hop question answering, yet routing every sub-query through a frontier model turns every hop into a cost multiplier and makes real-world deployment prohibitively expensive. Existing remedies either fix the r...