diff --git a/backends/arm/_passes/__init__.py b/backends/arm/_passes/__init__.py
index 52f14d326dd..d991c135e6c 100644
--- a/backends/arm/_passes/__init__.py
+++ b/backends/arm/_passes/__init__.py
@@ -5,6 +5,7 @@
 
 
 from . import arm_pass_utils  # noqa
+from . import fb
 from .arm_pass import ArmPass  # noqa  # usort: skip
 from .annotate_decomposed_matmul import AnnotateDecomposedMatmulPass  # noqa
 from .annotate_output_dim_order_pass import AnnotateOutputDimOrderPass  # noqa
@@ -80,6 +81,7 @@
 )
 from .decompose_var_pass import DecomposeVarPass  # noqa
 from .decorate_fp32_to_int32_casting_pass import DecorateFp32toInt32CastingPass  # noqa
+from .fb.reciprocal_dual_lut_pass import ReciprocalDualLutPass  # noqa
 from .fold_qdq_with_annotated_qparams_pass import (  # noqa
     FoldAndAnnotateQParamsPass,
     QuantizeClampArgumentsPass,
diff --git a/backends/arm/_passes/arm_pass_manager.py b/backends/arm/_passes/arm_pass_manager.py
index a3eafa5aac1..487beb736da 100644
--- a/backends/arm/_passes/arm_pass_manager.py
+++ b/backends/arm/_passes/arm_pass_manager.py
@@ -107,6 +107,7 @@
     RewriteConvPass,
     RewriteMatmulPass,
     RewriteUpsamplePass,
+    ReciprocalDualLutPass,
     ScalarsToAttributePass,
     SizeAdjustInputPass,
     ToTosaMemoryFormatPass,
@@ -329,6 +330,8 @@ def _tosa_pipeline(
                 FuseViewCopyTransformPass(),
                 DecomposeConvWithInt16ActivationPass(),
                 DecomposeSumPass(),
+                # FIX: Fixed LUT generation, re-enabled dual LUT pass
+                ReciprocalDualLutPass(exported_program),
                 InsertTableOpsPass(exported_program),
             ]
         )
diff --git a/backends/arm/test/ops/test_rsqrt.py b/backends/arm/test/ops/test_rsqrt.py
index b6a8ff687b7..1f444c91e6c 100644
--- a/backends/arm/test/ops/test_rsqrt.py
+++ b/backends/arm/test/ops/test_rsqrt.py
@@ -124,9 +124,6 @@ def test_rsqrt_tosa_INT_a16w8(test_tensor: torch.Tensor):
 
 @common.parametrize("test_tensor", Rsqrt.test_parameters)
 @common.XfailIfNoCorstone300
-@pytest.mark.xfail(
-    reason="MLETORCH-707: AssertionError: Output 0 does not match reference output."
-)
 def test_rsqrt_16a8w_u55_INT(test_tensor: torch.Tensor):
     """Test rsqrt operation with int16 I/O quantization for U55"""
     # Use wider tolerances for int16 I/O quantization on U55