mlsanityData to 14 Oct 2026

WebDancer: Towards Autonomous Information Seeking Agency

arXiv 2505.22648 ↗First posted 28 May 2025cs.CLcited by 188

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

Abstract (arXiv)

Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In this work, we present a cohesive paradigm for building end-to-end agentic information seeking agents from a data-centric and training-stage perspective. Our approach consists of four key stages: (1) browsing data construction, (2) trajectories sampling, (3) supervised fine-tuning for effective cold start, and (4) reinforcement learning for enhanced generalisation. We instantiate this framework in a web agent based on the ReAct, WebDancer. Empirical evaluations on the challenging information seeking benchmarks, GAIA and WebWalkerQA, demonstrate the strong performance of WebDancer, achieving considerable results and highlighting the efficacy of our training paradigm. Further analysis of agent training provides valuable insights and actionable, systematic pathways for developing more capable agentic models. The codes and demo will be released in https://github.com/Alibaba-NLP/WebAgent.

Key facts. Cited by 188 papers 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 54 of its 64 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

54 of 64 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning22 May
  2. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  3. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning10 Jan

Other references · 51

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  9. 2024Qwen2.5 Technical Reportcited by 4,942
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  12. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
38 more
  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  6. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  7. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
  8. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  9. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  10. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 497
  11. 2025Humanity's Last Examcited by 491
  12. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  13. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  14. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 336
  15. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 286
  16. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 282
  17. 2023FireAct: Toward Language Agent Fine-tuningcited by 256
  18. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 239
  19. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  20. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 145
  21. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  22. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  23. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  24. 2025Small Models Struggle to Learn from Strong Reasonerscited by 113
  25. 2024Symbolic Learning Enables Self-Evolving Agentscited by 106
  26. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 100
  27. 2022Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answeringcited by 72
  28. 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Modelcited by 63
  29. 2025Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solvingcited by 62
  30. 2025All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuningcited by 59
  31. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  32. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 30
  33. 2025API Agents vs. GUI Agents: Divergence and Convergencecited by 29
  34. 2025A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimizationcited by 21
  35. 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinkingcited by 18
  36. 2025Agent models: Internalizing Chain-of-Action Generation into Reasoning modelscited by 17
  37. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMscited by 16
  38. 2025Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Modelscited by 13

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 73; 2026: 115.

188 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 229
  3. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  4. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  5. 2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 150
  6. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 141
  7. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
  8. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  9. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  10. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 119
  11. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
  12. 2025WebExplorer: Explore and Evolve for Training Long-Horizon Web Agentscited by 92
38 more
  1. 2025MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scalingcited by 81
  2. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 80
  3. 2025Tree Search for LLM Agent Reinforcement Learningcited by 79
  4. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 71
  5. 2025WideSearch: Benchmarking Agentic Broad Info-Seekingcited by 69
  6. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 68
  7. 2025Tongyi DeepResearch Technical Reportcited by 66
  8. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 61
  9. 2025DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RLcited by 55
  10. 2025Towards General Agentic Intelligence via Environment Scalingcited by 54
  11. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligencecited by 54
  12. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  13. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 47
  14. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 47
  15. 2025WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Researchcited by 46
  16. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 44
  17. 2025MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agentscited by 42
  18. 2025Scaling Agents via Continual Pre-trainingcited by 40
  19. 2025Agentic Entropy-Balanced Policy Optimizationcited by 40
  20. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 39
  21. 2026Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Modelscited by 37
  22. 2026OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesiscited by 37
  23. 2025Search Self-play: Pushing the Frontier of Agent Capability without Supervisioncited by 34
  24. 2026Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Modelscited by 34
  25. 2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 33
  26. 2025CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agentscited by 33
  27. 2025SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graphcited by 28
  28. 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Executioncited by 27
  29. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 27
  30. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 27
  31. 2026SkillGrad: Optimizing Agent Skills Like Gradient Descentcited by 26
  32. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  33. 2025IterResearch: Rethinking Long-Horizon Agents with Interaction Scalingcited by 23
  34. 2026ExpSeek: Self-Triggered Experience Seeking for Web Agentscited by 23
  35. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 22
  36. 2026Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verificationcited by 22
  37. 2026OmniGAIA: Towards Native Omni-Modal AI Agentscited by 22
  38. 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agentscited by 21

50 most cited of 188 All 188 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
  2. 2026OpAgent: Operator Agent for Web Navigation
  3. 2025REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites
  4. 2026WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
  5. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  6. 2025InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
  7. 2025Go-Browse: Training Web Agents with Structured Exploration
  8. 2025Agentic Web: Weaving the Next Web with AI Agents