代码库
Can AI agents rebuild websites through browser exploration?
Python
agent-evaluationaiai-agentsbenchmarkbenchmarkingbrowser-automationbrowser-usefull-stackharborharbor-frameworkllmllm-benchmarkllm-benchmarkingllm-benchmarksreverse-engineeringswe-benchvisual-evaluationweb-agentsweb-developmentwebsite-reconstruction
Open-source benchmark for browser AI agents on daily tasks.
Python
agent-evaluationagentic-aiai-agent-benchmarkai-agentsbenchmarkbrowser-agentbrowser-automationbrowser-usechrome-agentchrome-extensioncomputer-usedatasetevaluationeveryday-tasksllmllm-evaluationonline-tasksreal-world-benchmarkweb-agentweb-agents
A version of verl to support diverse tool use [TMLR 2026]
Python
agentlearningllmreinforcement