Metraipolis › archive › dc_5a69ad002f86
EAGR: Evidence-Guided Adaptive Graph Retrieval — arXiv:2611.01910
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01910
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:52:45.275Z
- SHA-256 of the archived text
58e6911a4108606552942282bdd2767bbc062e70d394d50d0327a2a6dcf68139- Stable URL of this page
https://metraipolis.com/documento/dc_5a69ad002f86
How to cite
EAGR: Evidence-Guided Adaptive Graph Retrieval — arXiv:2611.01910 — arXiv (en), https://arxiv.org/abs/2611.01910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5a69ad002f86 (Metraipolis archive dc_5a69ad002f86, sha256 58e6911a4108606552942282bdd2767bbc062e70d394d50d0327a2a6dcf68139)
BibTeX
@misc{dc5a69ad002f86,
title = {EAGR: Evidence-Guided Adaptive Graph Retrieval — arXiv:2611.01910},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01910},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5a69ad002f86; sha256 58e6911a4108606552942282bdd2767bbc062e70d394d50d0327a2a6dcf68139},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-Augmented Generation (RAG) for multi-hop reasoning requires retrieval to adapt as intermediate evidence reveals new information needs. Existing approaches support such retrieval through explicit graph structures or iterative query reformulation, introducing graph-construction or query-time overhead. We present Evidence-Guided Adaptive Graph Retrieval (EAGR), a framework in which accumulated evidence dynamically determines which semantic directions to explore next, and which requires no dedicated graph database and no explicit graph materialization. EAGR operates over an implicit semantic graph induced by compact passage metadata pre-ingested into a standard VectorDB. Starting from dense-retrieval seed passages, an LLM iteratively assesses accumulated evidence, identifies promising semantic directions, expands the retrieval frontier through metadata-based neighborhood lookup, and terminates once sufficient evidence has been collected. By precomputing semantic metadata, EAGR enables evidence-conditioned graph exploration without materializing an explicit graph, maintaining a dedicated GraphDB, or iteratively rewriting the query. Across three widely used multi-hop QA benchmarks, EAGR achieves the highest LLM-based answer accuracy among evaluated methods, outperforming the vanilla RAG by 17\% and strongest graph-aware baseline by 4\% percentage points averaged across three popular benchmarks HotPotQA, 2WikiMultiHopQA, and MuSiQue. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.01910 — 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 2026-11-03T18:16:37.711Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).