Metraipolis › archive › dc_ce1c8789cefe
MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG — arXiv:2609.11065
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11065
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:23:44.622Z
- SHA-256 of the archived text
e2dda1dc0872536d928b8c3d345efe8b3381a096394c7e549b076d30ac11ca1a- Stable URL of this page
https://metraipolis.com/documento/dc_ce1c8789cefe
How to cite
MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG — arXiv:2609.11065 — arXiv (en), https://arxiv.org/abs/2609.11065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce1c8789cefe (Metraipolis archive dc_ce1c8789cefe, sha256 e2dda1dc0872536d928b8c3d345efe8b3381a096394c7e549b076d30ac11ca1a)
BibTeX
@misc{dcce1c8789cefe,
title = {MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG — arXiv:2609.11065},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11065},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce1c8789cefe; sha256 e2dda1dc0872536d928b8c3d345efe8b3381a096394c7e549b076d30ac11ca1a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 over seed selection, graph traversal, stopping, and evidence selection, while the corpus graph, indexes, scoring functions, grounding procedure, and answer generator remain shared. On GraphRAG-Bench, Mosaic achieves query-weighted Answer Correctness of 76.97 on Medical and 64.33 on Novel, improving over the strongest previously reported overall results by 5.13 and 4.43 points. On Medical, it reaches 95.1 Evidence Recall and 86.1 Context Relevancy. Controlled comparisons on an identical graph and generator show that no fixed narrow, medium, or wide policy is consistently optimal; Mosaic improves by 9.96 points over the strongest canonical fixed policy. Relative to Fixed Wide, it evaluates 81.9% fewer paths and retains 47.2% fewer evidence items. Transfer experiments on HotpotQA, MuSiQue, and 2WikiMultiHopQA further show that the policy interface can be applied without benchmark-specific retriever training. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.11065 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T05:17:51.966Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).