# WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents

arXiv: https://arxiv.org/abs/2404.05902 · HTML: https://mlsanity.com/paper/2404.05902/

## Key facts

- Cited by 22 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 19 of its 28 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://mlsanity.com/paper/2305.11854/) (2023)
- [LASER: LLM Agent with State-Space Exploration for Web Navigation](https://mlsanity.com/paper/2309.08172/) (2023)
- [Grounding Open-Domain Instructions to Automate Web Support Tasks](https://mlsanity.com/paper/2103.16057/) (2021)
- [Hierarchical Prompting Assists Large Language Model on Web Navigation](https://mlsanity.com/paper/2305.14257/) (2023)
- [BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions](https://mlsanity.com/paper/2310.06111/) (2023)

## Built on by (most cited first, 22 of 22)

- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems](https://mlsanity.com/paper/2407.13032/) (2024)
- [Beyond Browsing: API-Based Web Agents](https://mlsanity.com/paper/2410.16464/) (2024)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization](https://mlsanity.com/paper/2410.19609/) (2024)
- [A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions](https://mlsanity.com/paper/2501.16150/) (2025)
- [Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data](https://mlsanity.com/paper/2503.20749/) (2025)
- [AgentA/B: Automated and Scalable Web A/BTesting with Interactive LLM Agents](https://mlsanity.com/paper/2504.09723/) (2025)
- [WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms](https://mlsanity.com/paper/2504.11788/) (2025)
- [Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation](https://mlsanity.com/paper/2602.12544/) (2026)
- [Multimodal Auto Validation For Self-Refinement in Web Agents](https://mlsanity.com/paper/2410.00689/) (2024)
- [Reflection-Based Memory For Web navigation Agents](https://mlsanity.com/paper/2506.02158/) (2025)
- [DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer](https://mlsanity.com/paper/2507.23554/) (2025)
- [Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild](https://mlsanity.com/paper/2603.29020/) (2026)
- [MathViz-E: A Case-study in Domain-Specialized Tool-Using Agents](https://mlsanity.com/paper/2407.17544/) (2024)
- [WebLists: Extracting Structured Information From Complex Interactive Websites Using Executable LLM Agents](https://mlsanity.com/paper/2504.12682/) (2025)
- [VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2505.03181/) (2025)
- [WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale](https://mlsanity.com/paper/2510.16252/) (2025)
- [EmbeWebAgent: Embedding Web Agents into Any Customized UI](https://mlsanity.com/paper/2602.14865/) (2026)
- [Token Efficient Task Execution via Application Behavior Modeling for Web Agents](https://mlsanity.com/paper/2609.13491/) (2026)

## Abstract (arXiv)

In the realm of web agent research, achieving both generalization and accuracy remains a challenging problem. Due to high variance in website structure, existing approaches often fail. Moreover, existing fine-tuning and in-context learning techniques fail to generalize across multiple websites. We introduce Wilbur, an approach that uses a differentiable ranking model and a novel instruction synthesis technique to optimally populate a black-box large language model's prompt with task demonstrations from previous runs. To maximize end-to-end success rates, we also propose an intelligent backtracking mechanism that learns and recovers from its mistakes. Finally, we show that our ranking model can be trained on data from a generative auto-curriculum which samples representative goals from an LLM, runs the agent, and automatically evaluates it, with no manual annotation. Wilbur achieves state-of-the-art results on the WebVoyager benchmark, beating text-only models by 8% overall, and up to 36% on certain websites. On the same benchmark, Wilbur is within 5% of a strong multi-modal model despite only receiving textual inputs, and further analysis reveals a substantial number of failures are due to engineering challenges of operating the web.