DynamicRAG trains a reranker as an RL agent, using the generator's answer quality as reward to dynamically choose how many and which retrieved documents to pass forward.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
DynamicRAG trains a reranker as an RL agent, using the generator's answer quality as reward to dynamically choose how many and which retrieved documents to pass forward.