Unified ModelTask structure

rdagent/components/coder/model_coder/model.py

@@ -16,13 +16,14 @@ from rdagent.utils import get_module_by_module_path
 
 class ModelTask(Task):
     def __init__(
-        self, name: str, description: str, formulation: str, architecture: str, variables: Dict[str, str], model_type: Optional[str] = None
+        self, name: str, description: str, formulation: str, architecture: str, variables: Dict[str, str], hyperparameters: Dict[str, str], model_type: Optional[str] = None
     ) -> None:
         self.name: str = name
         self.description: str = description
         self.formulation: str = formulation
         self.architecture: str = architecture
         self.variables: str = variables
+        self.hyperparameters: str = hyperparameters
         self.model_type: str = model_type  # Tabular for tabular model, TimesSeries for time series model, Graph for graph model 
 
     def get_task_information(self):
@@ -31,6 +32,7 @@ description: {self.description}
 formulation: {self.formulation}
 architecture: {self.architecture}
 variables: {self.variables}
+hyperparameters: {self.hyperparameters}
 model_type: {self.model_type}
 """
 

rdagent/components/coder/model_coder/prompts.yaml

@@ -1,23 +1,41 @@
 extract_model_formulation_system: |-
     offer description of the proposed model in this paper, write a latex formula with variable as well as the architecture of the model. the format should be like 
-    "Model Name (replace with a reasonable model type)": {
-        "description": "",
-        "formulation": "",
-        "architecture": "",
+    {
+    "model_name (The name of the model)": {
+        "description": "A detailed description of the model",
+        "formulation": "A LaTeX formula representing the model's formulation",
+        "architecture": "A detailed description of the model's architecture, e.g., neural network layers or tree structures",
         "variables": {
-        "\\hat{y}_u": "The predicted output for node u",
-        }"
-        "model_type":"Tabular", "TimeSeries", or "Graph", (depending on which type of the model it is)
-        }
+            "\\hat{y}_u": "The predicted output for node u",
+            "variable_name_2": "Description of variable 2",
+            "variable_name_3": "Description of variable 3"
+        },
+        "hyperparameters": {
+            "hyperparameter_name_1": "value of hyperparameter 1",
+            "hyperparameter_name_2": "value of hyperparameter 2",
+            "hyperparameter_name_3": "value of hyperparameter 3"
+        },
+        "model_type": "Tabular or TimeSeries or Graph"  # Should be one of "Tabular", "TimeSeries", or "Graph"
+    }
+    }
     Eg. 
-    "ABC Model":{
-        "description": "",
-        "formulation": "",
-        "architecture": "",
+    {
+    "ABC Model": {
+        "description": "A detailed description of the model",
+        "formulation": "A LaTeX formula representing the model's formulation",
+        "architecture": "A detailed description of the model's architecture, e.g., neural network layers or tree structures",
         "variables": {
-        "\\hat{y}_u": "The predicted output for node u",
-        }"
-        "model_type":"Tabular",
+            "\\hat{y}_u": "The predicted output for node u",
+            "variable_name_2": "Description of variable 2",
+            "variable_name_3": "Description of variable 3"
+        },
+        "hyperparameters": {
+            "hyperparameter_name_1": "value of hyperparameter 1",
+            "hyperparameter_name_2": "value of hyperparameter 2",
+            "hyperparameter_name_3": "value of hyperparameter 3"
+        },
+        "model_type": "Tabular or TimeSeries or Graph"  # Should be one of "Tabular", "TimeSeries", or "Graph"
+    }
     }
     such format content should be begin with ```json and end with ``` and the content should be in json format.
 

rdagent/core/proposal.py

@@ -22,9 +22,10 @@ class Hypothesis:
     - Belief
     """
 
-    def __init__(self, hypothesis: str, reason: str) -> None:
+    def __init__(self, hypothesis: str, reason: str, concise_reason = str) -> None:
         self.hypothesis: str = hypothesis
         self.reason: str = reason
+        self.concise_reason: str = concise_reason
 
     def __str__(self) -> str:
         return f"""Hypothesis: {self.hypothesis}

rdagent/scenarios/qlib/prompts.yaml

@@ -12,7 +12,8 @@ hypothesis_output_format: |-
   The output should follow JSON format. The schema is as follows:
   {
     "hypothesis": "The new hypothesis generated based on the information provided.",
-    "reason": "The reason why you generate this hypothesis."
+    "reason": "The reason why you generate this hypothesis.",
+    "concise_reason": One line summary that focuses on the justification for the change that leads to the hypothesis (like a part of a knowledge that we are building),
   }
 
 model_hypothesis_specification: |-
@@ -85,13 +86,19 @@ model_experiment_output_format: |-
   {
     "model_name (The name of the model)": {
         "description": "A detailed description of the model",
+        "formulation": "A LaTeX formula representing the model's formulation",
         "architecture": "A detailed description of the model's architecture, e.g., neural network layers or tree structures",
+        "variables": {
+            "\\hat{y}_u": "The predicted output for node u",
+            "variable_name_2": "Description of variable 2",
+            "variable_name_3": "Description of variable 3"
+        },
         "hyperparameters": {
             "hyperparameter_name_1": "value of hyperparameter 1",
             "hyperparameter_name_2": "value of hyperparameter 2",
             "hyperparameter_name_3": "value of hyperparameter 3"
         },
-        "model_type": "Tabular or TimeSeries"  # Should be one of "Tabular" or "TimeSeries"
+        "model_type": "Tabular or TimeSeries  # Should be one of "Tabular" or "TimeSeries"
     }
   }
   Usually a larger model works better than a smaller one. Hence, the parameters should be larger.

rdagent/scenarios/qlib/proposal/model_proposal.py

@@ -39,7 +39,7 @@ class QlibModelHypothesisGen(ModelHypothesisGen):
 
     def convert_response(self, response: str) -> ModelHypothesis:
         response_dict = json.loads(response)
-        hypothesis = QlibModelHypothesis(hypothesis=response_dict["hypothesis"], reason=response_dict["reason"])
+        hypothesis = QlibModelHypothesis(hypothesis=response_dict["hypothesis"], reason=response_dict["reason"], concise_reason=response_dict["concise_reason"])
         return hypothesis
 
 
@@ -74,10 +74,12 @@ class QlibModelHypothesis2Experiment(ModelHypothesis2Experiment):
         tasks = []
         for model_name in response_dict:
             description = response_dict[model_name]["description"]
+            formulation = response_dict[model_name]["formulation"]
             architecture = response_dict[model_name]["architecture"]
+            variables = response_dict[model_name]["variables"]
             hyperparameters = response_dict[model_name]["hyperparameters"]
             model_type = response_dict[model_name]["model_type"]
-            tasks.append(ModelTask(model_name, description, architecture, hyperparameters, model_type))
+            tasks.append(ModelTask(model_name, description, formulation, architecture, variables, hyperparameters, model_type))
         exp = QlibModelExperiment(tasks)
         exp.based_experiments = [t[1] for t in trace.hist if t[2]]
         return exp