DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
Multi-hop retrieval-augmented generation (RAG) acquires evidence sequentially, with each new document potentially revealing missing facts, bridge entities, query defects, or sufficient support for answering. Existing methods provide useful operations such as iterative retrieval, query reformulation, evidence critique, and sufficiency judging, but typically organize them within method-specific pipelines or predefined control topologies. This leaves underexplored how to learn a shared state-conditioned policy that chooses among currently valid evidence operations. We introduce DynaKRAG, which fo
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%NirDiamant/RAG_Techniques →
- PossiblePossibly related (embedding) · 48%douglasjordan2/c0 →
- PossiblePossibly related (embedding) · 48%Tencent/WeKnora →
- PossiblePossibly related (embedding) · 47%telekom/wurzel →
- PossiblePossibly related (embedding) · 47%Retrieval is underrated →
- FuzzySimilar title/name (fuzzy) · 87%lllyasviel/ControlNet →
“Fuzzy title match (0.94): “DynaKRAG: A Unified Framework for Learnable Evidence Control” ≈ “lllyasviel/ControlNet””
- FuzzySimilar title/name (fuzzy) · 87%lllyasviel/ControlNet-v1-1 →
“Fuzzy title match (0.94): “DynaKRAG: A Unified Framework for Learnable Evidence Control” ≈ “lllyasviel/ControlNet-v1-1””
- LinkedLinked via arxiv author · 85%Yaqi Wu →
“DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation”