Skip to content

Bridging Static and Agentic RAG for Taiwanese Historical Question Answering

Sep 2026 · arXiv.org · Vol abs/2609.23056 · 0 citations · 25 references
Computer Science

TL;DR

A post-hoc selector is introduced that compares the two responses and their cited evidence, significantly outperforming either individual pipeline and recovering 60.34% of the oracle headroom.

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.

View source

Similar papers

Book Open access Nov 2026

Support Selection Survives under Official-Context RAG: A Same-Backbone Boundary Study

We study bounded Agentic retrieval-augmented generation (RAG) for knowledge-intensive question answering. The task is to answer multi-hop or domain questions from auditable external evidence under a fixed inference budget. Existing Agentic RAG evaluations often vary the model, retriever, corpus interface, controller, t...

Chuan-Heng Ma, Yi-Zhao Wang, Sheng-Yang Li · 0 citations
Preprint Oct 2026

Retrieval Augmented Generation Compositionality

It is shown that gains measured in isolation are not reliable predictors of realistic performance, and that new RAG techniques should be tested with the full surrounding stack, and called on researchers to do so and supply LASAGNA to simplify these experiments.

Ido Levy, Segev Shlomov, Leshem Choshen · 0 citations
#generative ai Review Open access Sep 2026

A Survey of conversational AI from rule based to generative and retrieval augmented generation chatbots

This survey presents a structured, design-oriented analysis of RAG-driven conversational systems through a principled framework that decomposes architectures along critical dimensions, including document segmentation and chunking strategies, embedding and indexing mechanisms, retriever and re-ranking models, knowledge...

V. Ghaywat, Abhyuday Singh, A. Shahade et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Adaptive Retrieval, Selective Answers: Evaluating Conformal Factuality in Agentic RAG

Retrieval-augmented generation (RAG) improves the grounding of language-model responses through external evidence, yet retrieved information alone does not ensure factual support for generated claims. In agentic RAG, evidence acquisition is further complicated by adaptive retrieval decisions, where an agent iteratively...

M. Rehman, Chi-Kuang Yeh · 0 citations
#machine learning Preprint Oct 2026

Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents

Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimization problem over many interacting choices, from chunking and embedding model to reranking and generation. Existing opti...

Lasse B. Strand, Robert Jakob, Kevin O'Sullivan et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks

Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers generated in the process, greatly relies on the effectiveness of retrieval mechanisms. In the realm of LLM, the last two years have seen tremendous progress in RAG archit...

Fazle Mohammed Tasfiq, Sabab Attin, Sheikh Md. Tahmid Hossain et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.