mlsanityData to 7 Oct 2026

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

arXiv 2503.20201 ↗First posted 26 Mar 2025cs.LG cs.CL cs.IRcited by 46

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and completes it by orchestrating a sequence of actions that includes calling tools, one of which is the Open Search Tool. Open Search Tool is a novel web search tool that outperforms proprietary counterparts. Together with powerful open-source reasoning LLMs, such as DeepSeek-R1, ODS nearly matches and sometimes surpasses the existing state-of-the-art baselines on two benchmarks: SimpleQA and FRAMES. For example, on the FRAMES evaluation benchmark, ODS improves the best existing baseline of the recently released GPT-4o Search Preview by 9.7% in accuracy. ODS is a general framework for seamlessly augmenting any LLMs -- for example, DeepSeek-R1 that achieves 82.4% on SimpleQA and 30.1% on FRAMES -- with search and reasoning capabilities to achieve state-of-the-art performance: 88.3% on SimpleQA and 75.3% on FRAMES.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 38 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

21 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation19 Sep

Other references · 20

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  8. 2023Large Language Modelscited by 774
  9. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  10. 2024Measuring short-form factuality in large language modelscited by 345
  11. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  12. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
8 more
  1. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 65
  2. 2024CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMscited by 15
  3. 2024Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responsescited by 15
  4. 2025Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Searchcited by 15
  5. 2024A Survey of Generative Search and Recommendation in the Era of Large Language Modelscited by 14
  6. 2024Generative AI Search Engines as Arbiters of Public Knowledge: An Audit of Bias and Authoritycited by 12
  7. 2024Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answerscited by 1
  8. 2025Semantica: Decentralized Search using a LLM-Guided Semantic Tree Overlaycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 35; 2026: 11.

46 papers.

Sort:

By area:

  1. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  2. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 144
  3. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 120
  4. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  5. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  6. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  7. 2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agentscited by 43
  8. 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 41
  9. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  10. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Modelscited by 35
  11. 2025MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agentscited by 35
  12. 2025DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesiscited by 31
34 more
  1. 2025ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquirycited by 30
  2. 2025SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agentscited by 29
  3. 2025MedBrowseComp: Benchmarking Medical Deep Research and Computer Usecited by 28
  4. 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Rewardcited by 25
  5. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoningcited by 24
  6. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answeringcited by 22
  7. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agentscited by 15
  8. 2025ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Frameworkcited by 11
  9. 2025Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Modelscited by 9
  10. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  11. 2025Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automationcited by 8
  12. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  13. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  14. 2025Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Themcited by 7
  15. 2025Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safetycited by 6
  16. 2025Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understandingcited by 6
  17. 2025DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shapingcited by 5
  18. 2025Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domainscited by 5
  19. 2026Is Agentic RAG worth it? An experimental comparison of RAG approachescited by 5
  20. 2025Efficient Tree-Structured Deep Research with Adaptive Resource Allocationcited by 4
  21. 2026Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Terminationcited by 4
  22. 2025Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanismscited by 3
  23. 2026IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agentscited by 3
  24. 2026ROMA: Recursive Open Meta-Agent Framework for Long-Horizon Multi-Agent Systemscited by 3
  25. 2025CHANCERY: Evaluating Corporate Governance Reasoning Capabilities in Language Modelscited by 2
  26. 2025A2Search: Ambiguity-Aware Question Answering with Reinforcement Learningcited by 2
  27. 2025Deep Research Agents Brings Deeper Harmcited by 2
  28. 2025KnowCoder-V2: Deep Knowledge Analysiscited by 1
  29. 2025Toward an AI-Native Internet: Rethinking the Web Architecture for Semantic Retrievalcited by 1
  30. 2026Evaluating Stochasticity in Deep Research Agentscited by 1
  31. 2026FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillationcited by 0
  32. 2026"Are You Sure?": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systemscited by 0
  33. 2026An Interactive Paradigm for Deep Researchcited by 0
  34. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
  2. 2025Improving and Evaluating Open Deep Research Agents
  3. 2025DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
  4. 2026EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
  5. 2025Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics
  6. 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
  7. 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
  8. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models