diff --git a/config/config2.example.yaml b/config/config2.example.yaml
index a7214f662..2a0ebcc47 100644
--- a/config/config2.example.yaml
+++ b/config/config2.example.yaml
@@ -81,6 +81,8 @@ exp_pool:
   persist_path: .chroma_exp_data # The directory.
   retrieval_type: bm25 # Default is `bm25`, can be set to `chroma` for vector storage, which requires setting up embedding.
   use_llm_ranker: true # Default is `true`, it will use LLM Reranker to get better result.
+  collection_name: experience_pool  # When `retrieval_type` is `chroma`, `collection_name` is the collection name in chromadb.
+
 
 azure_tts_subscription_key: "YOUR_SUBSCRIPTION_KEY"
 azure_tts_region: "eastus"
diff --git a/metagpt/configs/exp_pool_config.py b/metagpt/configs/exp_pool_config.py
index 8d33b25aa..a4a2d5d41 100644
--- a/metagpt/configs/exp_pool_config.py
+++ b/metagpt/configs/exp_pool_config.py
@@ -22,3 +22,4 @@ class ExperiencePoolConfig(YamlModel):
         default=ExperiencePoolRetrievalType.BM25, description="The retrieval type for experience pool."
     )
     use_llm_ranker: bool = Field(default=True, description="Use LLM Reranker to get better result.")
+    collection_name: str = Field(default="experience_pool", description="The collection name in chromadb")
diff --git a/metagpt/exp_pool/manager.py b/metagpt/exp_pool/manager.py
index e38906d90..2d50b052f 100644
--- a/metagpt/exp_pool/manager.py
+++ b/metagpt/exp_pool/manager.py
@@ -7,12 +7,7 @@ from pydantic import BaseModel, ConfigDict, Field
 
 from metagpt.config2 import Config
 from metagpt.configs.exp_pool_config import ExperiencePoolRetrievalType
-from metagpt.exp_pool.schema import (
-    DEFAULT_COLLECTION_NAME,
-    DEFAULT_SIMILARITY_TOP_K,
-    Experience,
-    QueryType,
-)
+from metagpt.exp_pool.schema import DEFAULT_SIMILARITY_TOP_K, Experience, QueryType
 from metagpt.logs import logger
 from metagpt.utils.exceptions import handle_exception
 
@@ -166,7 +161,7 @@ class ExperienceManager(BaseModel):
         retriever_configs = [
             ChromaRetrieverConfig(
                 persist_path=self.config.exp_pool.persist_path,
-                collection_name=DEFAULT_COLLECTION_NAME,
+                collection_name=self.config.exp_pool.collection_name,
                 similarity_top_k=DEFAULT_SIMILARITY_TOP_K,
             )
         ]
diff --git a/metagpt/exp_pool/schema.py b/metagpt/exp_pool/schema.py
index b119e5850..a45910f0d 100644
--- a/metagpt/exp_pool/schema.py
+++ b/metagpt/exp_pool/schema.py
@@ -7,7 +7,6 @@ from pydantic import BaseModel, Field
 
 MAX_SCORE = 10
 
-DEFAULT_COLLECTION_NAME = "experience_pool"
 DEFAULT_SIMILARITY_TOP_K = 2
 
 
diff --git a/metagpt/schema.py b/metagpt/schema.py
index 8ef7dd0bb..5f9a5667f 100644
--- a/metagpt/schema.py
+++ b/metagpt/schema.py
@@ -148,7 +148,7 @@ class SerializationMixin(BaseModel, extra="forbid"):
         serialized_data = self.model_dump()
 
         write_json_file(file_path, serialized_data)
-        logger.info(f"{self.__class__.__qualname__} serialization successful. File saved at: {file_path}")
+        logger.debug(f"{self.__class__.__qualname__} serialization successful. File saved at: {file_path}")
 
         return file_path
 
@@ -171,7 +171,7 @@ class SerializationMixin(BaseModel, extra="forbid"):
         data: dict = read_json_file(file_path)
 
         model = cls(**data)
-        logger.info(f"{cls.__qualname__} deserialization successful. Instance created from file: {file_path}")
+        logger.debug(f"{cls.__qualname__} deserialization successful. Instance created from file: {file_path}")
 
         return model