WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents
Abstract
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.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- AutoGuide: Automated Generation and Selection of State-Aware Guidelines for Large Language Model Agents (2024)
- BAGEL: Bootstrapping Agents by Guiding Exploration with Language (2024)
- Autonomous Evaluation and Refinement of Digital Agents (2024)
- AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent (2024)
- TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Wilbur: Revolutionizing Web Agents with Adaptive Learning
Links ๐:
๐ Subscribe: https://www.youtube.com/@Arxflix
๐ Twitter: https://x.com/arxflix
๐ LMNT (Partner): https://lmnt.com/
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper