developer tools
The Retriever Changed Its Route for Each Question
Mosaic used 81.9% fewer graph paths than a fixed-wide policy while improving answer scores on two GraphRAG domains.
Summary
Mosaic used 81.9% fewer graph paths than a fixed-wide policy while improving answer scores on two GraphRAG domains.
Direct facts, comparisons and mediated questions do not need the same graph traversal. Mosaic has an analyzer translate each query’s evidence needs into bounded choices for seeds, traversal, stopping and evidence selection while leaving the shared graph and answer generator unchanged. On GraphRAG-Bench it reports answer-correctness gains of 5.13 points in Medical and 4.43 in Novel over prior overall results. Against a fixed-wide policy on the same graph and generator, it evaluates 81.9% fewer paths and retains 47.2% fewer evidence items. Transfer tests support portability, though the results remain benchmark-specific.
Why it matters
Mosaic used 81.9% fewer graph paths than a fixed-wide policy while improving answer scores on two GraphRAG domains.
Limits and context
- Direct facts, comparisons and mediated questions do not need the same graph traversal.
- Transfer tests support portability, though the results remain benchmark-specific.
Key claims
Mosaic used 81.9% fewer graph paths than a fixed-wide policy while improving answer scores on two GraphRAG domains.
Qualification: Direct facts, comparisons and mediated questions do not need the same graph traversal.
Evidence: source-2026-09-11-006
Sources
- arXiv preprint 2609.11065arXiv · primary research
Corrections
No corrections have been recorded for this story.