LivingRAG: Augmenting Graph RAG with Experience
Graph-based RAG improves multi-hop question answering by organizing evidence as a knowledge graph. However, most existing RAG systems process each query in isolation and discard useful reasoning from the LLM's response after inference. As a result, later related queries need to retrieve evidence and reason from scratch. We propose LivingRAG, a Graph RAG framework with writable and reusable reasoning experience. LivingRAG adds a writable experience store to a graph-based retrieval backbone, enabling verified experiences to be reused during inference in two ways. Stored graph signals help retrie
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) · 27%microsoft/graphrag →
“Possibly related via embedding similarity 0.58 (not asserted). Timestamp check: artifact slightly before paper (-41d).”
- LinkedLinked via arxiv author · 85%Yuzhuo Cui →
“LivingRAG: Augmenting Graph RAG with Experience”
- LinkedLinked via arxiv author · 85%Zongye Zhang →
“LivingRAG: Augmenting Graph RAG with Experience”
- LinkedLinked via arxiv author · 85%Qingjie Liu →
“LivingRAG: Augmenting Graph RAG with Experience”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzySimilar title/name (fuzzy) · 59%tirth8205/code-review-graph →
“Fuzzy title match (0.73): “LivingRAG: Augmenting Graph RAG with Experience” ≈ “tirth8205/code-review-graph””