WebShop
Princeton simulated e-commerce environment and benchmark for grounded language agents shopping from text instructions.
Tags
Description
Established research environment from the 2022 WebShop paper (princeton-nlp/WebShop), not a new 2026 launch. MIT LICENSE.md verified; GitHub not archived (last push observed 2024-09). Provides a Gym-style web shopping sim with search agents for reproducing paper results. Setup uses Python 3.8+, Java and the repo setup.sh. Model inference and any external site access are separate.
Agent access
Related
- WebArena: A realistic web environment for building autonomous agents, with benchmark tasks used to evaluate web agents.
- WebVoyager: Multimodal end-to-end web agent research code and 643-task dataset across 15 real websites, with GPT-4V auto-eval protocol.
Sources
- https://webshop-pnlp.github.io/
- https://github.com/princeton-nlp/WebShop
- https://github.com/princeton-nlp/WebShop/blob/master/LICENSE.md
- https://arxiv.org/abs/2207.01206
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)