|
70 | 70 |
|
71 | 71 | ### 🌟 Key Highlights |
72 | 72 |
|
73 | | -- 🏆 **State-of-the-Art Performance**: #1 ranking across [multiple agentic benchmarks](https://miromindai.github.io/miroflow-private/v0.3/evaluation_overview/) |
| 73 | +- 🏆 **State-of-the-Art Performance**: #1 ranking across [multiple agentic benchmarks](https://miromindai.github.io/MiroFlow/evaluation_overview/) |
74 | 74 | - 📊 **Premium Training Data**: Curated datasets via [MiroVerse](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1) |
75 | 75 | - 🤖 **Open Models**: Complete collection at [MiroThinker](https://huggingface.co/collections/miromind-ai/mirothinker-v01-689301b6d0563321862d44a1) |
76 | 76 | - 🔧 **Full Training Stack**: SFT/DPO recipes at [MiroTrain](https://github.com/MiroMindAI/MiroTrain) |
@@ -137,11 +137,11 @@ uv run main.py trace --config_file_name=agent_quickstart_1 --task="What is the f |
137 | 137 | - **HLE**: Humanity's Last Exam. ([paper](https://arxiv.org/abs/2501.14249)) |
138 | 138 | - **HLE-Text-500**: A subset of HLE for text-only tasks. ([paper](https://arxiv.org/pdf/2504.21776)) |
139 | 139 |
|
140 | | -Follow our detailed guides to reproduce benchmark results in our [Benchmarks Documentation](https://miromindai.github.io/MiroFlow/v0.3/evaluation_overview/) |
| 140 | +Follow our detailed guides to reproduce benchmark results in our [Benchmarks Documentation](https://miromindai.github.io/MiroFlow/evaluation_overview/) |
141 | 141 |
|
142 | 142 | # 🤖 MiroFlow: AI Agentic Foundation Framework |
143 | 143 |
|
144 | | -MiroFlow is a high-performance, modular framework for building intelligent AI agents that deliver state-of-the-art results on complex reasoning tasks. The framework features advanced multi-turn conversation capabilities, extensive tool ecosystem integration, and hierarchical sub-agent orchestration for optimal task completion. Learn more about our agent [workflow architecture](https://miromindai.github.io/MiroFlow/v0.3/core_concepts/). |
| 144 | +MiroFlow is a high-performance, modular framework for building intelligent AI agents that deliver state-of-the-art results on complex reasoning tasks. The framework features advanced multi-turn conversation capabilities, extensive tool ecosystem integration, and hierarchical sub-agent orchestration for optimal task completion. Learn more about our agent [workflow architecture](https://miromindai.github.io/MiroFlow/core_concepts/). |
145 | 145 |
|
146 | 146 | <div align="center"> |
147 | 147 | <img src="docs/mkdocs/docs/assets/miroflow_architecture.png" width="100%" alt="MiroFlow Architecture"> |
@@ -172,7 +172,7 @@ Yes, MiroFlow supports various language models. Check our documentation for conf |
172 | 172 | <details> |
173 | 173 | <summary><strong>How do I reproduce the benchmark results?</strong></summary> |
174 | 174 | <br> |
175 | | -Follow our detailed <a href="https://miromindai.github.io/MiroFlow/v0.3/evaluation_overview/">Benchmarks Documentation</a> for step-by-step reproduction guides. |
| 175 | +Follow our detailed <a href="https://miromindai.github.io/MiroFlow/evaluation_overview/">Benchmarks Documentation</a> for step-by-step reproduction guides. |
176 | 176 | </details> |
177 | 177 |
|
178 | 178 | <details> |
|
0 commit comments