diff --git a/verl/workers/reward_manager/dapo.py b/verl/workers/reward_manager/dapo.py
index f44cb3d8f9d..0c43dc1f45d 100644
--- a/verl/workers/reward_manager/dapo.py
+++ b/verl/workers/reward_manager/dapo.py
@@ -118,7 +118,7 @@ def __call__(self, data: DataProto, return_dict: bool = False):
 
             reward = score
 
-            if self.overlong_buffer_cfg.enable:
+            if self.overlong_buffer_cfg is not None and self.overlong_buffer_cfg.enable:
                 overlong_buffer_len = self.overlong_buffer_cfg.len
                 expected_len = self.max_resp_len - overlong_buffer_len
                 exceed_len = valid_response_length - expected_len
@@ -129,7 +129,8 @@ def __call__(self, data: DataProto, return_dict: bool = False):
                     reward_extra_info["overlong_reward"].append(overlong_reward)
                     reward_extra_info["overlong"].append(overlong_reward < 0)
 
-            reward_tensor[i, valid_response_length - 1] = reward
+            if valid_response_length.item() > 0:
+                reward_tensor[i, valid_response_length.item() - 1] = reward
 
             if data_source not in already_print_data_sources:
                 already_print_data_sources[data_source] = 0
diff --git a/verl/workers/reward_manager/naive.py b/verl/workers/reward_manager/naive.py
index f3ca122c2b6..dea8e4d4f19 100644
--- a/verl/workers/reward_manager/naive.py
+++ b/verl/workers/reward_manager/naive.py
@@ -97,7 +97,8 @@ def __call__(self, data: DataProto, return_dict: bool = False) -> torch.Tensor |
             else:
                 reward = score
 
-            reward_tensor[i, valid_response_length - 1] = reward
+            if valid_response_length.item() > 0:
+                reward_tensor[i, valid_response_length.item() - 1] = reward
 
             if data_source not in already_print_data_sources:
                 already_print_data_sources[data_source] = 0
diff --git a/verl/workers/reward_manager/prime.py b/verl/workers/reward_manager/prime.py
index b15ed7c3fcb..6c0c234b64d 100644
--- a/verl/workers/reward_manager/prime.py
+++ b/verl/workers/reward_manager/prime.py
@@ -174,7 +174,8 @@ def __call__(self, data: DataProto, return_dict: bool = False) -> torch.Tensor |
 
         for i in range(len(data)):
             data_source = data_sources[i]
-            reward_tensor[i, valid_response_length[i].item() - 1] = scores[i]
+            if valid_response_length[i].item() > 0:
+                reward_tensor[i, valid_response_length[i].item() - 1] = scores[i]
 
             if data_source not in already_print_data_sources:
                 already_print_data_sources[data_source] = 0