EVO-RAG applies curriculum-guided reinforcement learning with time-varying reward weights to multi-hop RAG, reporting improved EM on HotpotQA, 2WikiMultiHopQA, and MuSiQue.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation
EVO-RAG applies curriculum-guided reinforcement learning with time-varying reward weights to multi-hop RAG, reporting improved EM on HotpotQA, 2WikiMultiHopQA, and MuSiQue.