arXiv cs.AI· Kai-Hsin Chen, Wei-Yu Chen, Xuanjun Chen, Jyh-Shing Roger Jang·· 17 小时前AI 评分31
结合静态与智能体 RAG 的台湾历史问答研究
Bridging Static and Agentic RAG for Taiwanese Historical Question Answering
AI 导读
研究对智能体 RAG 与静态 RAG 在台湾历史问答上做了受控对比，两者共享同一生成器与混合检索后端，总体性能相近但在 70.83% 的问题上结果不同、优势基本相互抵消。作者据此提出事后选择器，比较两个回答及其引用证据，显著优于任一单独流程，并回收了 oracle 上限的 60.34%；oracle 按题择优可让综合得分比更优的单流程高出 0.2417。
正文 · 原文
Abstract: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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2609.23056 [cs.CL] |
| (or arXiv:2609.23056v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.23056 arXiv-issued DOI via DataCite |
Submission history
From: Kai-Hsin Chen [view email]
[v1]
Sat, 19 Sep 2026 14:43:26 UTC (2,196 KB)
来源：arXiv cs.AI · arxiv.org