mlsanityData to 14 Oct 2026

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

arXiv 2512.13059 ↗First posted 15 Dec 2025cs.CLcited by 1

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 16 of its 20 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

16 of 20 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research24 Nov
  2. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL11 Aug
  3. 2025DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research25 May
  4. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan

Other references · 12

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  5. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 336
  6. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 335
  7. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  8. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  9. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  10. 2025Chain-of-Retrieval Augmented Generationcited by 49
  11. 2024Long2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recallcited by 32
  12. 2025SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agentscited by 31

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Deep Research: A Systematic Survey
  2. 2026DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
  3. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
  4. 2025A Survey of Large Language Model Agents for Question Answering
  5. 2025Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms
  6. 2025YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering
  7. 2025Deep Research: A Survey of Autonomous Research Agents
  8. 2026DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents