# An Open and Reproducible Deep Research Agent for Long-Form Question Answering

Source: [An Open and Reproducible Deep Research Agent for Long-Form Question Answering](<https://www.sota2.com/research/paper/6940e7aa456146936284f8d2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-17T05:04:46.379Z

Authors: Ikuya Yamada, Wataru Ikeda, Ko Yoshida, Mengyu Ye, Hinata Sugimoto, Masatoshi Suzuki, Hisanori Ozaki, Jun Suzuki

Published: 2025-12-15T07:37:53.000Z

## Abstract

We present an open deep research system for long-form question answering, selected as a winning system in the text-to-text track of the MMU-RAG competition at NeurIPS 2025. The system combines an open-source large language model (LLM) with an open web search API to perform iterative retrieval, reasoning, and synthesis in real-world open-domain settings. To enhance reasoning quality, we apply preference tuning based on LLM-as-a-judge feedback that evaluates multiple aspects, including clarity, insightfulness, and factuality. Our experimental results show that the proposed method consistently improves answer quality across all three aspects. Our source code is publicly available at https://github.com/efficient-deep-research/efficient-deep-research.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.13059>)

[PDF](<https://arxiv.org/pdf/2512.13059.pdf>)