An Open and Reproducible Deep Research Agent for Long-Form Question Answering
This provides an open and reproducible solution for researchers and practitioners needing high-quality long-form answers in open-domain settings, though it appears incremental in combining existing techniques.
The authors tackled long-form question answering by developing an open deep research system that combines an open-source LLM with web search and preference tuning, achieving consistent improvements in clarity, insightfulness, and factuality as demonstrated in the MMU-RAG competition at NeurIPS 2025.
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.