World of Bits: An Open-Domain Platform for Web-Based Agents
Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, Percy Liang
- 🏛 Institutions
- Stanford, OpenAI
- 📅 Date
- August 31, 2017
- 📑 Publisher
- ICML 2017
- 💻 Env
- Web
- 🔑 Keywords
TLDR
World of Bits is an open-domain web environment where agents observe rendered webpages and DOM structure, then act with low-level keyboard and mouse commands. The paper also defines a methodology for building reproducible web tasks from real websites, including MiniWoB and QAWoB.
Related papers
- Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement LearningMay 1, 2024 · SAC 2024
- Reinforcement Learning on Web Interfaces Using Workflow-Guided ExplorationFebruary 24, 2018 · ICLR 2018 (Poster)
- AndroidEnv: A Reinforcement Learning Platform for AndroidMay 27, 2021 · arXiv
- WebArena-Infinity: Generating Browser Environments with Verifiable Tasks at ScaleMarch 2026 · Blog Post
- WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web AgentsMarch 5, 2026 · arXiv
- OpAgent: Operator Agent for Web NavigationFebruary 14, 2026 · arXiv