mlsanityData to 14 Oct 2026

Go-Browse: Training Web Agents with Structured Exploration

arXiv 2506.03533 ↗First posted 4 Jun 2025cs.CLcited by 33

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

Abstract (arXiv)

One of the fundamental problems in digital agents is their lack of understanding of their environment. For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To address this, we propose Go-Browse, a method for automatically collecting diverse and realistic web agent data at scale through structured exploration of web environments. Go-Browse achieves efficient exploration by framing data collection as a graph search, enabling reuse of information across exploration episodes. We instantiate our method on the WebArena benchmark, collecting a dataset of 10K successful task-solving trajectories and 40K interaction steps across 100 URLs. Fine-tuning a 7B parameter language model on this dataset achieves a success rate of 21.7% on the WebArena benchmark, beating GPT-4o mini by 2.4% and exceeding current state-of-the-art results for sub-10B parameter models by 2.9%.

Key facts. Cited by 33 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 26 of its 33 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

26 of 33 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills9 Apr
  2. 2025Inducing Programmatic Skills for Agentic Tasks9 Apr
  3. 2025An Illusion of Progress? Assessing the Current State of Web Agents2 Apr
  4. 2025Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents17 Feb
  5. 2025InSTA: Towards Internet-Scale Training For Agents10 Feb
  6. 2024Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents17 Dec
  7. 2024The BrowserGym Ecosystem for Web Agent Research6 Dec
  8. 2024ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data22 Nov
  9. 2024Beyond Browsing: API-Based Web Agents21 Oct
  10. 2024NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild3 Oct
  11. 2024Agent Workflow Memory11 Sep
  12. 2024AutoWebGLM: A Large Language Model-based Web Navigating Agent4 Apr
2 more
  1. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?12 Mar
  2. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul

Other references · 12

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2024Qwen2 Technical Reportcited by 2,120
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  4. 2018Exploration by Random Network Distillationcited by 993
  5. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  6. 2020First return, then explorecited by 266
  7. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 212
  8. 2024OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesiscited by 163
  9. 2024Autonomous Evaluation and Refinement of Digital Agentscited by 137
  10. 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scalecited by 43
  11. 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Languagecited by 34
  12. 2025AutoEval: A Practical Framework for Autonomous Evaluation of Mobile Agentscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 25.

33 papers.

Sort:

By area:

  1. 2025OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflowscited by 57
  2. 2025AgentSynth: Scalable Task Generation for Generalist Computer-Use Agentscited by 46
  3. 2025PolySkill: Learning Generalizable Skills Through Polymorphic Abstractioncited by 27
  4. 2026Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Taskscited by 18
  5. 2025Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agentscited by 17
  6. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 16
  7. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 14
  8. 2026DynaWeb: Model-Based Reinforcement Learning of Web Agentscited by 14
  9. 2026OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesiscited by 11
  10. 2025WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environmentcited by 10
  11. 2026Agentic Test-Time Scaling for WebAgentscited by 8
  12. 2026PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Taskscited by 7
21 more
  1. 2025Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chaincited by 6
  2. 2026ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolutioncited by 6
  3. 2026WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agentscited by 6
  4. 2026Generalization in Online Reinforcement Learning for Mobile Agentscited by 6
  5. 2026Self-Improvement of Large Language Models: A Technical Overview and Future Outlookcited by 5
  6. 2026ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agentscited by 5
  7. 2026Structured Distillation of Web Agent Capabilities Enables Generalizationcited by 3
  8. 2026Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?cited by 2
  9. 2026ProCUA-SFT Technical Reportcited by 2
  10. 2026Scalable Behaviour Cloning on Browser Using via Skill Distillationcited by 2
  11. 2026Discriminative World Models for Web Agentscited by 2
  12. 2026EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprisescited by 1
  13. 2026WebChallenger: A Reliable and Efficient Generalist Web Agentcited by 1
  14. 2026SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstractioncited by 1
  15. 2026DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learningcited by 0
  16. 2026KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planningcited by 0
  17. 2026Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNavcited by 0
  18. 2026Using Grounded Theory for Agent Behavior Analysis at Scalecited by 0
  19. 2026FinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priorscited by 0
  20. 2026X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalizationcited by 0
  21. 2026AMBER: Training Long-Horizon Web Agents through Append-Only Memorycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
  2. 2026GTA: Generating Long-Horizon Tasks for Web Agents at Scale
  3. 2025BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
  4. 2026Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
  5. 2026UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp
  6. 2025Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
  7. 2025WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks
  8. 2025REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites