Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,8 @@ Unlike previous agents that scale only model size or context length, MiroThinker
|
|
| 39 |
|
| 40 |
Empirical results demonstrate the effectiveness of this interactive scaling. Performance across several benchmarks improves predictably as the model engages in increasingly deep and frequent interactions with its environment.
|
| 41 |
|
|
|
|
|
|
|
| 42 |
**Key Features**
|
| 43 |
|
| 44 |
- MiroThinker v1.0 supports a 256K context window, long-horizon reasoning, and deep multi-step analysis.
|
|
|
|
| 39 |
|
| 40 |
Empirical results demonstrate the effectiveness of this interactive scaling. Performance across several benchmarks improves predictably as the model engages in increasingly deep and frequent interactions with its environment.
|
| 41 |
|
| 42 |
+

|
| 43 |
+
|
| 44 |
**Key Features**
|
| 45 |
|
| 46 |
- MiroThinker v1.0 supports a 256K context window, long-horizon reasoning, and deep multi-step analysis.
|