Update README.md
Browse files
README.md
CHANGED
|
@@ -58,6 +58,9 @@ Where:
|
|
| 58 |
- $\alpha_i = \exp(-\delta \cdot i/T)$ implements exponential decay for later reasoning steps
|
| 59 |
- $\mathcal{L}_{\text{QS}}$ is the quality scoring loss ensuring reasoning coherence
|
| 60 |
|
|
|
|
|
|
|
|
|
|
| 61 |
#### Dynamic Weight Adjustment Mechanism
|
| 62 |
|
| 63 |
The complexity-aware weight adjustment is formulated as:
|
|
|
|
| 58 |
- $\alpha_i = \exp(-\delta \cdot i/T)$ implements exponential decay for later reasoning steps
|
| 59 |
- $\mathcal{L}_{\text{QS}}$ is the quality scoring loss ensuring reasoning coherence
|
| 60 |
|
| 61 |
+
$a_o$
|
| 62 |
+
|
| 63 |
+
|
| 64 |
#### Dynamic Weight Adjustment Mechanism
|
| 65 |
|
| 66 |
The complexity-aware weight adjustment is formulated as:
|