diff --git a/test/stdlib/components/intrinsic/test_rag.py b/test/stdlib/components/intrinsic/test_rag.py
index b8a8b42aa..0b60be9e6 100644
--- a/test/stdlib/components/intrinsic/test_rag.py
+++ b/test/stdlib/components/intrinsic/test_rag.py
@@ -115,6 +115,7 @@ def test_query_rewrite(backend):
     assert result == expected
 
 
+@pytest.mark.xfail(reason="Non-deterministic citation boundaries across environments")
 @pytest.mark.qualitative
 def test_citations(backend):
     """Verify that the citations intrinsic functions properly."""