mlsanityData to 7 Oct 2026

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

arXiv 2307.12856 ↗First posted 24 Jul 2023cs.LG cs.AI cs.CLcited by 350

Not on the map. Why?

Cited by 256 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world websites has still suffered from (1) open domainness, (2) limited context length, and (3) lack of inductive bias on HTML. We introduce WebAgent, an LLM-driven agent that learns from self-experience to complete tasks on real websites following natural language instructions. WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites via Python programs generated from those. We design WebAgent with Flan-U-PaLM, for grounded code generation, and HTML-T5, new pre-trained LLMs for long HTML documents using local and global attention mechanisms and a mixture of long-span denoising objectives, for planning and summarization. We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks; achieving 18.7% higher success rate than the prior method on MiniWoB web automation benchmark, and SoTA performance on Mind2Web, an offline task planning evaluation.

Key facts. Cited by 350 papers in the map (data through 7 Oct 2026). Builds on 82 of its 101 references that are in the map. First posted on arXiv 24 Jul 2023.

Builds on

82 of 101 references.

References · 82

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  7. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  8. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  9. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  10. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  11. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  12. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
38 more
  1. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2021Program Synthesis with Large Language Modelscited by 3,509
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2022Emergent Abilities of Large Language Modelscited by 2,483
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  9. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  10. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  11. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  12. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  13. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  14. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  15. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  16. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  17. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  18. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  19. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  20. 2023PaLM 2 Technical Reportcited by 1,154
  21. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  22. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  23. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  24. 2021Measuring Coding Challenge Competence With APPScited by 879
  25. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  26. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  27. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  28. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  29. 2022PAL: Program-aided Language Modelscited by 635
  30. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  31. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  32. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  33. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  34. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  35. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  36. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  37. 2023Language Models can Solve Computer Taskscited by 371
  38. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 27; 2024: 110; 2025: 136; 2026: 77.

350 papers.

Sort:

By area:

  1. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  4. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  5. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 584
  6. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  7. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  8. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  9. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  10. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 442
  11. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Modelscited by 424
  12. 2023Cognitive Architectures for Language Agentscited by 422
38 more
  1. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 407
  2. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  3. 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agentscited by 373
  4. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?cited by 348
  5. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  6. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactioncited by 271
  7. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  8. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  9. 2025ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Usecited by 246
  10. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
  11. 2024ShowUI: One Vision-Language-Action Model for GUI Visual Agentcited by 226
  12. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 226
  13. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  14. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 201
  15. 2024GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devicescited by 190
  16. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  17. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 187
  18. 2024On the Effects of Data Scale on UI Control Agentscited by 187
  19. 2023You Only Look at Screens: Multimodal Chain-of-Action Agentscited by 185
  20. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 182
  21. 2024WebLINX: Real-World Website Navigation with Multi-Turn Dialoguecited by 177
  22. 2023A Simple LLM Framework for Long-Range Video Question-Answeringcited by 176
  23. 2024Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMscited by 173
  24. 2025An Illusion of Progress? Assessing the Current State of Web Agentscited by 165
  25. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 162
  26. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  27. 2024OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Webcited by 156
  28. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?cited by 155
  29. 2024The BrowserGym Ecosystem for Web Agent Researchcited by 152
  30. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  31. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agentscited by 144
  32. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
  33. 2024Autonomous Evaluation and Refinement of Digital Agentscited by 136
  34. 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agentscited by 135
  35. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  36. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  37. 2024WebCanvas: Benchmarking Web Agents in Online Environmentscited by 119
  38. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116

50 most cited of 350 All 350 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Models Can Self-Improve At Web Agent Tasks
  2. 2025BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
  3. 2024AutoWebGLM: A Large Language Model-based Web Navigating Agent
  4. 2026WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
  5. 2025WALT: Web Agents that Learn Tools
  6. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
  7. 2026Learning Simple Test-Time Environments for LLM Web Agents
  8. 2026WebXSkill: Skill Learning for Autonomous Web Agents