diff --git a/ablkit/data/evaluation/reasoning_metric.py b/ablkit/data/evaluation/reasoning_metric.py
index 7fb8855..63d66ea 100644
--- a/ablkit/data/evaluation/reasoning_metric.py
+++ b/ablkit/data/evaluation/reasoning_metric.py
@@ -1,6 +1,6 @@
 """
 This module contains the ReasoningMetric, which is used for evaluating the model performance
-on tasks need reasoning.
+on tasks that need reasoning.
 
 Copyright (c) 2024 LAMDA.  All rights reserved.
 """
@@ -14,7 +14,7 @@ from .base_metric import BaseMetric
 
 class ReasoningMetric(BaseMetric):
     """
-    A metrics class for evaluating the model performance on tasks need reasoning.
+    A metrics class for evaluating the model performance on tasks that need reasoning.
 
     This class is designed to calculate the accuracy of the reasoing results. Reasoning
     results are generated by first using the learning part to predict pseudo-labels
diff --git a/ablkit/reasoning/reasoner.py b/ablkit/reasoning/reasoner.py
index a016c3c..a44acd9 100644
--- a/ablkit/reasoning/reasoner.py
+++ b/ablkit/reasoning/reasoner.py
@@ -258,8 +258,9 @@ class Reasoner:
 
     def zoopt_budget(self, symbol_num: int) -> int:
         """
-        Set the budget for ZOOpt optimization. The function, in its default implementation,
-        returns a budget value of 10 * ``symbol_num``.
+        Set the budget for ZOOpt optimization. The budget can be dynamic relying on 
+        the number of symbols considered, e.g., the default implementation shown below. 
+        Alternatively, it can be a fixed value, such as simply setting it to 100.
 
         Parameters
         ----------
@@ -269,7 +270,7 @@ class Reasoner:
         Returns
         -------
         int
-            The budget for ZOOpt optimization. By default, this is 10 * ``symbol_num``.
+            The budget for ZOOpt optimization.
         """
         return 10 * symbol_num