diff --git a/libs/langchain/langchain/document_loaders/arxiv.py b/libs/langchain/langchain/document_loaders/arxiv.py
index 0cfde95afa..a3da66223d 100644
--- a/libs/langchain/langchain/document_loaders/arxiv.py
+++ b/libs/langchain/langchain/document_loaders/arxiv.py
@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import Any, List, Optional
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
@@ -9,25 +9,18 @@ class ArxivLoader(BaseLoader):
     """Load a query result from `Arxiv`.
 
     The loader converts the original PDF format into the text.
+
+    Args:
+        Supports all arguments of `ArxivAPIWrapper`.
     """
 
     def __init__(
-        self,
-        query: str,
-        load_max_docs: Optional[int] = 100,
-        load_all_available_meta: Optional[bool] = False,
+        self, query: str, doc_content_chars_max: Optional[int] = None, **kwargs: Any
     ):
         self.query = query
-        """The query to be passed to the arxiv.org API."""
-        self.load_max_docs = load_max_docs
-        """The maximum number of documents to load."""
-        self.load_all_available_meta = load_all_available_meta
-        """Whether to load all available metadata."""
+        self.client = ArxivAPIWrapper(
+            doc_content_chars_max=doc_content_chars_max, **kwargs
+        )
 
     def load(self) -> List[Document]:
-        arxiv_client = ArxivAPIWrapper(
-            load_max_docs=self.load_max_docs,
-            load_all_available_meta=self.load_all_available_meta,
-        )
-        docs = arxiv_client.load(self.query)
-        return docs
+        return self.client.load(self.query)