SOURCE-LINKED INTELLIGENCE

MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Graph Retrieval-Augmented Generation (GraphRAG) can connect evidence distributed across a corpus graph, but most systems use largely shared exploration procedures across queries. This creates a structural mismatch: direct facts may need compact local neighborhoods, comparisons need balanced coverage of multiple targets, and mediated questions may require deeper paths through weakly related connectors. We present Mosaic, a training-free framework that formulates GraphRAG retrieval as a per-query control problem. An LLM analyzer converts query-specific evidence requirements into a bounded policy

Read original source ↗ Open in workspace

recordType

paper

region

Global