Metraipolis › archive › dc_4aca9829488d
Bridging Static and Agentic RAG for Taiwanese Historical Question Answering — arXiv:2609.23056
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23056
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:43.137Z
- SHA-256 of the archived text
93f73f431efd0fe4a3000d7a6fc2ec7232190cb3741db43b742c894cb030b174- Stable URL of this page
https://metraipolis.com/documento/dc_4aca9829488d
How to cite
Bridging Static and Agentic RAG for Taiwanese Historical Question Answering — arXiv:2609.23056 — arXiv (en), https://arxiv.org/abs/2609.23056 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4aca9829488d (Metraipolis archive dc_4aca9829488d, sha256 93f73f431efd0fe4a3000d7a6fc2ec7232190cb3741db43b742c894cb030b174)
BibTeX
@misc{dc4aca9829488d,
title = {Bridging Static and Agentic RAG for Taiwanese Historical Question Answering — arXiv:2609.23056},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23056},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4aca9829488d; sha256 93f73f431efd0fe4a3000d7a6fc2ec7232190cb3741db43b742c894cb030b174},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23056. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic retrieval-augmented generation (RAG) enables language models to adapt retrieval based on previously retrieved evidence, but it remains unclear whether such adaptive orchestration consistently outperforms well-designed static pipelines. We conduct a controlled comparison of agentic and static RAG for Taiwanese historical question answering, sharing the same generator and hybrid retrieval backend. Despite similar aggregate performance, the two pipelines differ on 70.83% of questions, with their advantages largely canceling out when averaged. An oracle that selects the better response per question improves the composite score by 0.2417 over the better individual pipeline, revealing substantial headroom for question-level selection. We therefore introduce a post-hoc selector that compares the two responses and their cited evidence, significantly outperforming either individual pipeline and recovering 60.34% of the oracle headroom. These results show that aggregate comparisons can obscure meaningful question-level differences between retrieval strategies, suggesting that exploiting their complementarity may be more fruitful than seeking a universally superior pipeline. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.23056 — 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 2026-10-09T06:48:44.970Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).