Metraipolis › archive › dc_bc404ff758d3

Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering — arXiv:2609.00761

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00761
License (as archived): CC0-1.0
Archived: 2026-10-17T06:43:43.845Z
SHA-256 of the archived text: d20efd16a73b633228182fe4b78775db1176adc5c335667d020736a3f7d8924e
Stable URL of this page: https://metraipolis.com/documento/dc_bc404ff758d3

How to cite

Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering — arXiv:2609.00761 — arXiv (en), https://arxiv.org/abs/2609.00761 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc404ff758d3 (Metraipolis archive dc_bc404ff758d3, sha256 d20efd16a73b633228182fe4b78775db1176adc5c335667d020736a3f7d8924e)

BibTeX

@misc{dcbc404ff758d3,
  title = {Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering — arXiv:2609.00761},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00761},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc404ff758d3; sha256 d20efd16a73b633228182fe4b78775db1176adc5c335667d020736a3f7d8924e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00761. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Academic question answering requires reasoning over heterogeneous scholarly graphs, where queries range from simple attribute lookups to multi-hop inference across author--paper--venue structures. Existing retrieval-augmented generation (RAG) systems struggle in this setting due to three limitations: (1) fixed retrieval strategies that do not adapt to varying query complexity, (2) the absence of sufficiency evaluation leading to incomplete or misaligned evidence, and (3) a lack of structured verification against graph facts. To address these issues, we propose an agentic heterogeneous graph RAG method that transforms the three core stages of the RAG pipeline into explicit agentic decision steps. A query-aware retrieval agent analyzes query type and selects an appropriate graph traversal strategy; a sufficiency-aware reranking agent assesses evidence completeness and adaptively expands the retrieved subgraph; and a graph-grounded verification agent checks entity, relation, and attribute correctness before finalizing the answer. Experiments on heterogeneous graphs constructed from OpenAlex and DBLP suggest that our method consistently outperforms strong LLM, graph-augmented RAG, and agent-based baselines.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-02 in cs.SI).
Categorie arXiv: Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2609.00761 — 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 2026-10-17T06:37:58.288Z dalla pagina https://arxiv.org/catchup/cs.SI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).