diff --git a/docs/source/adding_benchmarks.mdx b/docs/source/adding_benchmarks.mdx
index 73a951276..77ccd3d4a 100644
--- a/docs/source/adding_benchmarks.mdx
+++ b/docs/source/adding_benchmarks.mdx
@@ -26,7 +26,7 @@ During evaluation, data moves through four stages:
 1. gym.Env  ──→  raw observations (numpy dicts)
 
 2. Preprocessing  ──→  standard LeRobot keys + task description
-   (preprocess_observation, add_envs_task in envs/utils.py)
+   (preprocess_observation in envs/utils.py, env.call("task_description"))
 
 3. Processors  ──→  env-specific then policy-specific transforms
    (env_preprocessor, policy_preprocessor)
@@ -161,6 +161,8 @@ class MyBenchmarkEnv(gym.Env):
         ...
 ```
 
+**GPU-based simulators (e.g. MuJoCo with EGL rendering):** If your simulator allocates GPU/EGL contexts during `__init__`, defer that allocation to a `_ensure_env()` helper called on first `reset()`/`step()`. This avoids inheriting stale GPU handles when `AsyncVectorEnv` spawns worker processes. See `LiberoEnv._ensure_env()` for the pattern.
+
 Also provide a factory function that returns the nested dict structure:
 
 ```python
@@ -207,7 +209,7 @@ class MyBenchmarkEnvConfig(EnvConfig):
     def gym_kwargs(self) -> dict:
         return {"obs_type": self.obs_type, "render_mode": self.render_mode}
 
-    def create_envs(self, n_envs: int, use_async_envs: bool = False):
+    def create_envs(self, n_envs: int, use_async_envs: bool = True):
         """Override for multi-task benchmarks or custom env creation."""
         from lerobot.envs.<benchmark> import create_<benchmark>_envs
         return create_<benchmark>_envs(task=self.task, n_envs=n_envs, ...)