kohjingyu/search-agents
Code for the paper 🌳 Tree Search for Language Model Agents
This project helps AI researchers evaluate how well language model agents can navigate and perform multi-step tasks in complex, interactive online environments like e-commerce sites or social media platforms. You provide access to various simulated web environments and API keys for large language models, and the system outputs performance metrics and detailed agent trajectories. This is ideal for researchers studying advanced AI planning and exploration with language models.
220 stars. No commits in the last 6 months.
Use this if you are an AI researcher developing and testing language model agents for complex, multi-step tasks in web environments and need a robust framework for evaluation.
Not ideal if you are looking for a ready-to-use tool to automate web tasks for business or personal use, as this is a research framework for agent development.
Stars
220
Forks
24
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/kohjingyu/search-agents"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FutureAGI/Xenoverse
Benchmarking general decision-making with open & random worlds
helios-base/helios-base
HELIOS base is a sample implementation of the simulated soccer team for the RoboCup Soccer Simulation.
google-deepmind/lab
A customisable 3D platform for agent-based AI research
helios-base/librcsc
A base library to develop a simulated soccer team for the RoboCup Soccer Simulation
google-deepmind/lab2d
A customisable 2D platform for agent-based AI research