diff --git a/src/lerobot/policies/evo1/modeling_evo1.py b/src/lerobot/policies/evo1/modeling_evo1.py
index a81a0705a..b9369f4b0 100644
--- a/src/lerobot/policies/evo1/modeling_evo1.py
+++ b/src/lerobot/policies/evo1/modeling_evo1.py
@@ -42,6 +42,9 @@ class Evo1Policy(PreTrainedPolicy):
     config_class = Evo1Config
     name = "evo1"
 
+    def supports_rtc(self) -> bool:
+        return True
+
     def __init__(self, config: Evo1Config, *, vlm_hub_kwargs: dict | None = None, **kwargs):
         super().__init__(config)
         config.validate_features()
diff --git a/src/lerobot/policies/groot/modeling_groot.py b/src/lerobot/policies/groot/modeling_groot.py
index 415af9309..8c5dfba34 100644
--- a/src/lerobot/policies/groot/modeling_groot.py
+++ b/src/lerobot/policies/groot/modeling_groot.py
@@ -68,6 +68,9 @@ class GrootPolicy(PreTrainedPolicy):
     name = "groot"
     config_class = GrootConfig
 
+    def supports_rtc(self) -> bool:
+        return True
+
     def __init__(self, config: GrootConfig, **kwargs):
         """Initialize Groot policy wrapper."""
         require_package("transformers", extra="groot")
diff --git a/src/lerobot/policies/molmoact2/modeling_molmoact2.py b/src/lerobot/policies/molmoact2/modeling_molmoact2.py
index 14d9e19e2..b05091900 100644
--- a/src/lerobot/policies/molmoact2/modeling_molmoact2.py
+++ b/src/lerobot/policies/molmoact2/modeling_molmoact2.py
@@ -520,6 +520,9 @@ class MolmoAct2Policy(PreTrainedPolicy):
     config_class = MolmoAct2Config
     name = "molmoact2"
 
+    def supports_rtc(self) -> bool:
+        return self.config.inference_action_mode == "continuous"
+
     def __init__(
         self,
         config: MolmoAct2Config,
diff --git a/src/lerobot/policies/pi0/modeling_pi0.py b/src/lerobot/policies/pi0/modeling_pi0.py
index 7a444f97f..aca9112b2 100644
--- a/src/lerobot/policies/pi0/modeling_pi0.py
+++ b/src/lerobot/policies/pi0/modeling_pi0.py
@@ -749,6 +749,9 @@ class PI0Policy(PreTrainedPolicy):
     config_class = PI0Config
     name = "pi0"
 
+    def supports_rtc(self) -> bool:
+        return True
+
     def __init__(
         self,
         config: PI0Config,
diff --git a/src/lerobot/policies/pi05/modeling_pi05.py b/src/lerobot/policies/pi05/modeling_pi05.py
index d45f5a5c2..ee19fd5ab 100644
--- a/src/lerobot/policies/pi05/modeling_pi05.py
+++ b/src/lerobot/policies/pi05/modeling_pi05.py
@@ -714,6 +714,9 @@ class PI05Policy(PreTrainedPolicy):
     config_class = PI05Config
     name = "pi05"
 
+    def supports_rtc(self) -> bool:
+        return True
+
     def __init__(
         self,
         config: PI05Config,
diff --git a/src/lerobot/policies/pretrained.py b/src/lerobot/policies/pretrained.py
index 0283f389a..8823e5808 100644
--- a/src/lerobot/policies/pretrained.py
+++ b/src/lerobot/policies/pretrained.py
@@ -249,6 +249,10 @@ class PreTrainedPolicy(nn.Module, HubMixin, abc.ABC):
         """
         raise NotImplementedError
 
+    def supports_rtc(self) -> bool:
+        """Whether this policy implements Real-Time Chunking inference semantics."""
+        return False
+
     # TODO(aliberts, rcadene): split into 'forward' and 'compute_loss'?
     @abc.abstractmethod
     def forward(self, batch: dict[str, Tensor]) -> tuple[Tensor, dict | None]:
diff --git a/src/lerobot/policies/smolvla/modeling_smolvla.py b/src/lerobot/policies/smolvla/modeling_smolvla.py
index 7f54d03f0..2ac63b994 100644
--- a/src/lerobot/policies/smolvla/modeling_smolvla.py
+++ b/src/lerobot/policies/smolvla/modeling_smolvla.py
@@ -145,6 +145,9 @@ class SmolVLAPolicy(PreTrainedPolicy):
     config_class = SmolVLAConfig
     name = "smolvla"
 
+    def supports_rtc(self) -> bool:
+        return True
+
     def __init__(
         self,
         config: SmolVLAConfig,
diff --git a/src/lerobot/rollout/context.py b/src/lerobot/rollout/context.py
index cf69d57b5..e4974561b 100644
--- a/src/lerobot/rollout/context.py
+++ b/src/lerobot/rollout/context.py
@@ -57,6 +57,7 @@ from .inference import (
     SyncInferenceConfig,
     create_inference_engine,
 )
+from .inference.rtc import supports_rtc_inference
 from .robot_wrapper import ThreadSafeRobot
 
 if TYPE_CHECKING or _peft_available:
@@ -226,6 +227,12 @@ def build_rollout_context(
     policy = _load_pretrained_policy(policy_config)
 
     if is_rtc:
+        if not supports_rtc_inference(policy):
+            raise ValueError(
+                f"RTC inference is not supported by policy type '{policy_config.type}': "
+                "the policy must implement RTC semantics and predict_action_chunk must accept "
+                "inference_delay and prev_chunk_left_over. Use '--inference.type=sync' instead."
+            )
         policy.config.rtc_config = cfg.inference.rtc
         if hasattr(policy, "init_rtc_processor"):
             policy.init_rtc_processor()
diff --git a/src/lerobot/rollout/inference/rtc.py b/src/lerobot/rollout/inference/rtc.py
index 0eef62cef..8ff44998a 100644
--- a/src/lerobot/rollout/inference/rtc.py
+++ b/src/lerobot/rollout/inference/rtc.py
@@ -22,6 +22,7 @@ way via ``notify_observation``.
 
 from __future__ import annotations
 
+import inspect
 import logging
 import math
 import time
@@ -62,6 +63,23 @@ _RTC_JOIN_TIMEOUT_S: float = 3.0
 # ---------------------------------------------------------------------------
 
 
+def supports_rtc_inference(policy: PreTrainedPolicy) -> bool:
+    """Whether a policy declares RTC support and accepts the RTC call shape."""
+    supports_rtc = getattr(policy, "supports_rtc", None)
+    if not callable(supports_rtc) or not supports_rtc():
+        return False
+
+    try:
+        inspect.signature(policy.predict_action_chunk).bind(
+            object(),
+            inference_delay=0,
+            prev_chunk_left_over=None,
+        )
+    except (TypeError, ValueError):
+        return False
+    return True
+
+
 def _normalize_prev_actions_length(prev_actions: torch.Tensor, target_steps: int) -> torch.Tensor:
     """Pad or truncate RTC prefix actions to a fixed length for stable compiled inference."""
     if prev_actions.ndim != 2: