diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
index 64d874a31c428..09616cc38212b 100644
--- a/pandas/core/groupby/groupby.py
+++ b/pandas/core/groupby/groupby.py
@@ -3272,7 +3272,10 @@ def first(x: Series):
                 """Helper function for first item that isn't NA."""
                 arr = x.array[notna(x.array)]
                 if not len(arr):
-                    return np.nan
+                    nan_arr = x.array[isna(x.array)]
+                    if not len(nan_arr):
+                        return np.nan
+                    return nan_arr[0]
                 return arr[0]
 
             if isinstance(obj, DataFrame):
@@ -3331,7 +3334,10 @@ def last(x: Series):
                 """Helper function for last item that isn't NA."""
                 arr = x.array[notna(x.array)]
                 if not len(arr):
-                    return np.nan
+                    nan_arr = x.array[isna(x.array)]
+                    if not len(nan_arr):
+                        return np.nan
+                    return nan_arr[-1]
                 return arr[-1]
 
             if isinstance(obj, DataFrame):
diff --git a/pandas/tests/extension/json/test_json.py b/pandas/tests/extension/json/test_json.py
index 0920e70142446..fb2208b304f9e 100644
--- a/pandas/tests/extension/json/test_json.py
+++ b/pandas/tests/extension/json/test_json.py
@@ -356,10 +356,6 @@ def test_groupby_extension_no_sort(self):
         """
         super().test_groupby_extension_no_sort()
 
-    @pytest.mark.xfail(reason="GH#39098: Converts agg result to object")
-    def test_groupby_agg_extension(self, data_for_grouping):
-        super().test_groupby_agg_extension(data_for_grouping)
-
 
 class TestArithmeticOps(BaseJSON, base.BaseArithmeticOpsTests):
     def test_arith_frame_with_scalar(self, data, all_arithmetic_operators, request):
diff --git a/pandas/tests/extension/test_boolean.py b/pandas/tests/extension/test_boolean.py
index 63ae2b629e549..fb8e8803bdbb3 100644
--- a/pandas/tests/extension/test_boolean.py
+++ b/pandas/tests/extension/test_boolean.py
@@ -48,7 +48,7 @@ def data_for_twos(dtype):
 
 @pytest.fixture
 def data_missing(dtype):
-    return pd.array([np.nan, True], dtype=dtype)
+    return pd.array([pd.NA, True], dtype=dtype)
 
 
 @pytest.fixture
@@ -58,7 +58,7 @@ def data_for_sorting(dtype):
 
 @pytest.fixture
 def data_missing_for_sorting(dtype):
-    return pd.array([True, np.nan, False], dtype=dtype)
+    return pd.array([True, pd.NA, False], dtype=dtype)
 
 
 @pytest.fixture
@@ -76,7 +76,7 @@ def na_value():
 def data_for_grouping(dtype):
     b = True
     a = False
-    na = np.nan
+    na = pd.NA
     return pd.array([b, b, na, na, a, a, b], dtype=dtype)
 
 
@@ -147,7 +147,7 @@ def _check_op(self, obj, op, other, op_name, exc=NotImplementedError):
                 expected = expected.astype("Float64")
             if op_name == "__rpow__":
                 # for rpow, combine does not propagate NaN
-                expected[result.isna()] = np.nan
+                expected[result.isna()] = pd.NA
             self.assert_equal(result, expected)
         else:
             with pytest.raises(exc):