arXiv Artificial Intelligence

MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG

2 hours ago 12.09.2026 07:00 👁 1 views
MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG

Quick summary

arXiv:2609.11065v1 Announce Type: new Abstract: 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-spec

Key takeaways

  • arXiv:2609.11065v1 Announce Type: new Abstract: 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.

Why it matters

The significance is not only the legal text but how it changes product design. Decisions around “MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG” may reshape data collection, model training, output accountability and market access.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗