mlsanityData to 7 Oct 2026

Tongyi DeepResearch Technical Report

arXiv 2510.24701 ↗First posted 28 Oct 2025cs.CL cs.AI cs.IRcited by 53

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

Abstract (arXiv)

We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across complex tasks. We design a highly scalable data synthesis pipeline that is fully automatic, without relying on costly human annotation, and empowers all training stages. By constructing customized environments for each stage, our system enables stable and consistent interactions throughout. Tongyi DeepResearch, featuring 30.5 billion total parameters, with only 3.3 billion activated per token, achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510. We open-source the model, framework, and complete solutions to empower the community.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 37 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

24 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning16 Sep
  2. 2025WebSailor: Navigating Super-human Reasoning for Web Agent3 Jul
  3. 2025WebDancer: Towards Autonomous Information Seeking Agency28 May

Other references · 21

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  4. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  5. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  6. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 446
  7. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  8. 2025Small Language Models are the Future of Agentic AIcited by 254
  9. 2025UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learningcited by 205
  10. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  11. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 158
  12. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 139
9 more
  1. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 132
  2. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 118
  3. 2025Reinforcement Learning for Long-Horizon Interactive LLM Agentscited by 103
  4. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 66
  5. 2025Towards General Agentic Intelligence via Environment Scalingcited by 51
  6. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 45
  7. 2025WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Researchcited by 44
  8. 2025Scaling Agents via Continual Pre-trainingcited by 39
  9. 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routingcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 49.

53 papers.

Sort:

By area:

  1. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interactioncited by 33
  2. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 32
  3. 2026Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Modelscited by 30
  4. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 24
  5. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  6. 2026Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoningcited by 20
  7. 2026Immersion in the GitHub Universe: Scaling Coding Agents to Masterycited by 20
  8. 2026BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?cited by 20
  9. 2026Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verificationcited by 19
  10. 2025Thinking with Programming Vision: Towards a Unified View for Thinking with Imagescited by 13
  11. 2026MemoBrain: Executive Memory as an Agentic Brain for Reasoningcited by 12
  12. 2026Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Designcited by 12
38 more
  1. 2026O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RLcited by 10
  2. 2025Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Modelscited by 8
  3. 2026Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?cited by 8
  4. 2026QUEST: Training Frontier Deep Research Agents with Fully Synthetic Taskscited by 8
  5. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  6. 2026Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agentscited by 8
  7. 2026WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoningcited by 7
  8. 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoningcited by 6
  9. 2025PRInTS: Reward Modeling for Long-Horizon Information Seekingcited by 5
  10. 2026W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agentscited by 5
  11. 2026SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agentscited by 5
  12. 2026DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Datacited by 5
  13. 2026Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoningcited by 5
  14. 2026ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibrationcited by 4
  15. 2026CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verificationcited by 4
  16. 2026Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videoscited by 4
  17. 2026AREX: Towards a Recursively Self-Improving Agent for Deep Researchcited by 4
  18. 2025HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discoverycited by 3
  19. 2026Reasoning over mathematical objects: on-policy reward modeling and test time aggregationcited by 3
  20. 2026R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoningcited by 3
  21. 2026Learning to Retrieve from Agent Trajectoriescited by 3
  22. 2026Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoningcited by 3
  23. 2026TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generationcited by 3
  24. 2026Agents-K1: Towards Agent-native Knowledge Orchestrationcited by 3
  25. 2026Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agentcited by 2
  26. 2026Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Treescited by 2
  27. 2026TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learningcited by 1
  28. 2026Fine-Tuning Small Reasoning Models for Quantum Field Theorycited by 1
  29. 2026DRACULA: Hunting for the Actions Users Want Deep Research Agents to Executecited by 1
  30. 2026Efficient Agentic Reasoning Through Self-Regulated Simulative Planningcited by 1
  31. 2026FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Searchcited by 1
  32. 2026Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Modelscited by 0
  33. 2026TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Modelscited by 0
  34. 2026Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seekingcited by 0
  35. 2026PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneitycited by 0
  36. 2026Mint-Agent: Introducing Finance-Native Agentic Foundation Modelscited by 0
  37. 2026MidTool: Mid-training Data Synthesis for Agentic Tool Usecited by 0
  38. 2026Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Groundingcited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
  2. 2025Deep Research: A Survey of Autonomous Research Agents
  3. 2025Deep Research: A Systematic Survey
  4. 2025Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs
  5. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
  6. 2026DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
  7. 2026LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
  8. 2025ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework