NaviRAG organizes documents hierarchically and uses an LLM agent for active navigation across granularity levels to raise retrieval recall and answer quality on long-document QA tasks.
Example output: 2//Production Growth//The city achieved an agricultural product processing industry output value of 4.41 billion yuan, an increase of 11.7%
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation
NaviRAG organizes documents hierarchically and uses an LLM agent for active navigation across granularity levels to raise retrieval recall and answer quality on long-document QA tasks.