From 5e108d23593240db069598bc1bfb5ee4774db0b8 Mon Sep 17 00:00:00 2001 From: reacher-z Date: Mon, 27 Jul 2026 18:08:59 +0800 Subject: [PATCH] docs: reference ClawBench as complementary benchmark --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index a24a5dd..2475381 100644 --- a/README.md +++ b/README.md @@ -97,6 +97,8 @@ Our evaluation suite covers desktop, mobile, and web environments: * **Web**: `WebArenaLite-v2` (A refined version of WebArena-Lite suitable for visual-based agents) * **Windows**: `WindowsAgentArena` +For a complementary live-web browser-agent benchmark outside this evaluation suite, see [ClawBench](https://github.com/TIGER-AI-Lab/ClawBench); this external reference does not imply ScaleCUA integration or support. + ## 🧠 Training The directory `agent-sft/` contains all the necessary code and configuration files to train the ScaleCUA from scratch using our ScaleCUA-Data. We support training Computer Use Agents with both [InternVL](agent-sft/internvl_chat/README.md) and [Qwen-VL](agent-sft/qwen-vl-finetune/README.md).