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.
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· Proceedings of the 35th ACM...· 0 citations
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.
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.· Discover Artificial Intellig...· 0 citations
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...
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
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· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
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.