Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@ our model attains leading performance among small-scale models on multiple long-
|
|
| 30 |
|
| 31 |
ToolMind-web-3B delivers high-quality long-horizon reasoning and tool-augmented search capabilities while maintaining a lightweight 3B parameter footprint. Despite its compact size, it achieves competitive performance across multiple benchmarks like **GAIA, HLE, Xbench-Deepsearch**. The model is evaluated under the **[MiroThinkers workflow](https://github.com/MiroMindAI/MiroThinker)**, ensuring standardized and reproducible assessment.
|
| 32 |
|
| 33 |
-
2. **An Open-Source Complex QA Dataset Synthesized from Wikipedia Entity–Relation Knowledge Graphs** - Comming soon
|
| 34 |
|
| 35 |
We provide a rich, structured QA dataset derived from Wikipedia knowledge graphs, designed to support supervised fine-tuning and reinforcement learning of search-augmented agents.
|
| 36 |
|
|
|
|
| 30 |
|
| 31 |
ToolMind-web-3B delivers high-quality long-horizon reasoning and tool-augmented search capabilities while maintaining a lightweight 3B parameter footprint. Despite its compact size, it achieves competitive performance across multiple benchmarks like **GAIA, HLE, Xbench-Deepsearch**. The model is evaluated under the **[MiroThinkers workflow](https://github.com/MiroMindAI/MiroThinker)**, ensuring standardized and reproducible assessment.
|
| 32 |
|
| 33 |
+
2. **An Open-Source Complex QA Dataset Synthesized from Wikipedia Entity–Relation Knowledge Graphs** - **Comming soon**
|
| 34 |
|
| 35 |
We provide a rich, structured QA dataset derived from Wikipedia knowledge graphs, designed to support supervised fine-tuning and reinforcement learning of search-augmented agents.
|
| 36 |
|