From e80e9ba15bf1118ce15807eb1dc6d35075785aef Mon Sep 17 00:00:00 2001 From: Yifan Zhang <442943984@qq.com> Date: Wed, 21 Jan 2026 22:31:54 +0800 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 8e013139..8c4b79b7 100644 --- a/README.md +++ b/README.md @@ -22,11 +22,11 @@ -> **MiroThinker** is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark. +> **MiroThinker** is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark. The project currently comprises four key components: -- 💡 **MiroThinker**: An open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark. See [Quick Start](#-quick-start). +- 💡 **MiroThinker**: An open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark. See [Quick Start](#-quick-start). - 🤖 **MiroFlow**: An agent framework that enables tool-use agent tasks, featuring a reproducible GAIA score of 82.4%. See [MiroFlow](https://github.com/MiroMindAI/MiroFlow) for details. - 📚 **MiroVerse**: A premium open-source training dataset with 147k samples supporting research agent training. See [MiroVerse](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1) on HuggingFace.