diff --git a/rdagent/scenarios/data_science/proposal/exp_gen/prompts_v2.yaml b/rdagent/scenarios/data_science/proposal/exp_gen/prompts_v2.yaml
index 69f5174f..9daf8b0f 100644
--- a/rdagent/scenarios/data_science/proposal/exp_gen/prompts_v2.yaml
+++ b/rdagent/scenarios/data_science/proposal/exp_gen/prompts_v2.yaml
@@ -158,8 +158,8 @@ task_gen:
 
     Your final output should strictly adhere to the following JSON format. 
     {
-      "task_design": [Partial Response Format 1],
-      {% if workflow_check %}"workflow_update": [Partial Response Format 2], {% endif %}
+      "task_design": ---The dict corresponding to task output format---,
+      {% if workflow_check %}"workflow_update": ---A string corresponding to workflow description--- {% endif %}
     }
     
   user: |-
@@ -214,4 +214,4 @@ output_format:
           "risk_reward_balance_score": "The risk-reward balance of implementing the proposed hypothesis.",
         }
       },
-    }
\ No newline at end of file
+    }