mlsanityData to 14 Oct 2026

Bridging Static and Agentic RAG for Taiwanese Historical Question Answering

arXiv 2609.23056 ↗First posted 19 Sep 2026cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval also fits: Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 24 references that are in the map. First posted on arXiv 19 Sep 2026.

Builds on

13 of 24 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar

Other references · 12

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  4. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  5. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  6. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  7. 2024RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generationcited by 61
  8. 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Modelscited by 8
  9. 2026Is Agentic RAG worth it? An experimental comparison of RAG approachescited by 5
  10. 2025A Preliminary Study of RAG for Taiwanese Historical Archivescited by 4
  11. 2026CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learningcited by 3
  12. 2026Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAGcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  2. 2026Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
  3. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  4. 2026Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspective
  5. 2025RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG
  6. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  7. 2026LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
  8. 2026VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy