diff --git a/rdagent/app/qlib_rd_loop/factor.py b/rdagent/app/qlib_rd_loop/factor.py
index 4330702e..664d3ca0 100644
--- a/rdagent/app/qlib_rd_loop/factor.py
+++ b/rdagent/app/qlib_rd_loop/factor.py
@@ -36,11 +36,22 @@ qlib_factor_summarizer: HypothesisExperiment2Feedback = import_class(PROP_SETTIN
 trace = Trace(scen=scen)
 for _ in range(PROP_SETTING.evolving_n):
     try:
-        hypothesis = hypothesis_gen.gen(trace)
-        exp = hypothesis2experiment.convert(hypothesis, trace)
-        exp = qlib_factor_coder.develop(exp)
-        exp = qlib_factor_runner.develop(exp)
-        feedback = qlib_factor_summarizer.generateFeedback(exp, hypothesis, trace)
+        with logger.tag("r"):  # research
+            hypothesis = hypothesis_gen.gen(trace)
+            logger.log_object(hypothesis, tag="hypothesis generation")
+
+            exp = hypothesis2experiment.convert(hypothesis, trace)
+            logger.log_object(exp.sub_tasks, tag="experiment generation")
+
+        with logger.tag("d"):
+            exp = qlib_factor_coder.develop(exp)
+            logger.log_object(exp.sub_workspace_list)
+
+        with logger.tag("ef"):
+            exp = qlib_factor_runner.develop(exp)
+            logger.log_object(exp, tag="factor runner result")
+            feedback = qlib_factor_summarizer.generateFeedback(exp, hypothesis, trace)
+            logger.log_object(feedback, tag="feedback")
 
         trace.hist.append((hypothesis, exp, feedback))
     except FactorEmptyException as e:
diff --git a/rdagent/app/qlib_rd_loop/model.py b/rdagent/app/qlib_rd_loop/model.py
index 6a397a0c..3147bbc6 100644
--- a/rdagent/app/qlib_rd_loop/model.py
+++ b/rdagent/app/qlib_rd_loop/model.py
@@ -33,14 +33,20 @@ trace = Trace(scen=scen)
 with logger.tag("model.loop"):
     for _ in range(PROP_SETTING.evolving_n):
         try:
-            with logger.tag("r"): # research
+            with logger.tag("r"):  # research
                 hypothesis = hypothesis_gen.gen(trace)
+                logger.log_object(hypothesis, tag="hypothesis generation")
+
                 exp = hypothesis2experiment.convert(hypothesis, trace)
-            with logger.tag("d"): # develop
+                logger.log_object(exp.sub_tasks, tag="experiment generation")
+            with logger.tag("d"):  # develop
                 exp = qlib_model_coder.develop(exp)
-            with logger.tag("ef"): # evaluate and feedback
+                logger.log_object(exp.sub_workspace_list, tag="model coder result")
+            with logger.tag("ef"):  # evaluate and feedback
                 exp = qlib_model_runner.develop(exp)
+                logger.log_object(exp, tag="model runner result")
                 feedback = qlib_model_summarizer.generateFeedback(exp, hypothesis, trace)
+                logger.log_object(feedback, tag="feedback")
             trace.hist.append((hypothesis, exp, feedback))
         except ModelEmptyException as e:
             logger.warning(e)
diff --git a/rdagent/components/coder/factor_coder/factor.py b/rdagent/components/coder/factor_coder/factor.py
index 5c9b7390..6d244d25 100644
--- a/rdagent/components/coder/factor_coder/factor.py
+++ b/rdagent/components/coder/factor_coder/factor.py
@@ -108,8 +108,7 @@ class FactorFBWorkspace(FBWorkspace):
             if self.raise_exception:
                 raise CodeFormatException(self.FB_CODE_NOT_SET)
             else:
-                # TODO: to make the interface compatible with previous code. I kept the original behavior.
-                raise ValueError(self.FB_CODE_NOT_SET)
+                return self.FB_CODE_NOT_SET, None
         with FileLock(self.workspace_path / "execution.lock"):
             if FACTOR_IMPLEMENT_SETTINGS.enable_execution_cache:
                 # NOTE: cache the result for the same code and same data type
diff --git a/rdagent/core/evolving_agent.py b/rdagent/core/evolving_agent.py
index f030df64..c9e76b2d 100644
--- a/rdagent/core/evolving_agent.py
+++ b/rdagent/core/evolving_agent.py
@@ -5,6 +5,7 @@ from tqdm import tqdm
 
 from rdagent.core.evaluation import Evaluator
 from rdagent.core.evolving_framework import EvolvableSubjects, EvoStep, Feedback
+from rdagent.log import rdagent_logger as logger
 
 
 class EvoAgent(ABC):
@@ -13,12 +14,14 @@ class EvoAgent(ABC):
         self.evolving_strategy = evolving_strategy
 
     @abstractmethod
-    def multistep_evolve(self, evo: EvolvableSubjects, eva: Evaluator | Feedback, **kwargs: Any) -> EvolvableSubjects:
-        ...
+    def multistep_evolve(
+        self, evo: EvolvableSubjects, eva: Evaluator | Feedback, **kwargs: Any
+    ) -> EvolvableSubjects: ...
 
     @abstractmethod
-    def filter_evolvable_subjects_by_feedback(self, evo: EvolvableSubjects, feedback: Feedback) -> EvolvableSubjects:
-        ...
+    def filter_evolvable_subjects_by_feedback(
+        self, evo: EvolvableSubjects, feedback: Feedback
+    ) -> EvolvableSubjects: ...
 
 
 class RAGEvoAgent(EvoAgent):
@@ -53,6 +56,7 @@ class RAGEvoAgent(EvoAgent):
                 evolving_trace=self.evolving_trace,
                 queried_knowledge=queried_knowledge,
             )
+            logger.log_object(evo.sub_workspace_list, tag=f"evolving code")
 
             # 4. Pack evolve results
             es = EvoStep(evo, queried_knowledge)
@@ -62,6 +66,7 @@ class RAGEvoAgent(EvoAgent):
                 es.feedback = (
                     eva if isinstance(eva, Feedback) else eva.evaluate(evo, queried_knowledge=queried_knowledge)
                 )
+                logger.log_object(es.feedback, tag=f"evolving feedback")
 
             # 6. update trace
             self.evolving_trace.append(es)