cs.CLNov 19, 2026

AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development

Authors: Hang Zhang, Yuzhi Pan, Ziyao Zhong, Chaokun Wang, Shuo Cao, Zeyu Huang, Yue Xue, Fang Niu, 

Organizations: School of Software, Tsinghua University, Beijing, China · Sina Weibo Corp, Beijing, China

Abstract

Retrieval-augmented generation (RAG) is a well-established paradigm for augmenting large language models (LLMs) with information retrieved from external corpora. However, developing effective RAG systems requires substantial engineering effort and iterative experimentation, as effective design choices vary across tasks and domains. With rapid advances in LLM agent capabilities, we ask how well these agents can autonomously build RAG systems and how effectively they can improve them through iteration. In this paper, we propose AutoRAGBench, the first benchmark to evaluate how well LLM agents develop RAG systems from scratch in an open code space. It comprises nine RAG system development tasks. For each task, agents build RAG systems from scratch without starter code or prescribed strategies, under a six-hour budget on a single H800 GPU. They analyze task data, implement RAG pipelines, and iteratively refine their designs based on experimental feedback. We evaluate nine agent configurations and analyze both the effectiveness of the resulting RAG systems and their development trajectories. GPT-6.1 Sol with Codex CLI achieves the highest average score of 56.1. The composite Human-SOTA baseline averages 44.4. These results show that LLM agents can automate effective RAG system development. When starting from a human-designed system on each of seven tasks, GPT-6.1 Sol with Codex CLI improves the score by 16.6 points on average.

Figures & tables

Explore similar work

CardsList
  1. LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation

    Mar 6, 2026Koki Itai, Shunichi Hasegawa, Yuta Yamamoto +2RAG EvaluationLLM Evaluation

  2. AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning

    Apr 19, 2026Jingbo Sun, Wenyue Chong, Songjun Tu +7Agentic RetrievalAgentic RAG