diff --git a/docs/training/rlhf.md b/docs/training/rlhf.md
index 2aae267e1d..ccce0f37dd 100644
--- a/docs/training/rlhf.md
+++ b/docs/training/rlhf.md
@@ -18,6 +18,8 @@ The following open-source RL libraries use vLLM for fast rollouts (sorted alphab
 
 For weight synchronization between training and inference, see the [Weight Transfer](weight_transfer/README.md) documentation, which covers the pluggable backend system with [NCCL](weight_transfer/nccl.md) (multi-GPU) and [IPC](weight_transfer/ipc.md) (same-GPU) engines. To verify that an update landed on every rank, see the [Weight Checker](weight_checker.md).
 
+For MoE policies, see [Routed Experts Return](routed_experts.md) (`--enable-return-routed-experts`) to get the per-token expert routing of each rollout for routing replay (R3) in the trainer.
+
 For pipelining generation and training to improve GPU utilization and throughput, see the [Async Reinforcement Learning](async_rl.md) guide, which covers the pause/resume API for safely updating weights mid-flight.
 
 See the following notebooks showing how to use vLLM for GRPO:
diff --git a/docs/training/routed_experts.md b/docs/training/routed_experts.md
new file mode 100644
index 0000000000..f531a0ebbd
--- /dev/null
+++ b/docs/training/routed_experts.md
@@ -0,0 +1,54 @@
+# Routed Experts Return (MoE Routing Replay / R3)
+
+`--enable-return-routed-experts` makes vLLM return the routed experts (the expert IDs each MoE layer's router selected) for every token of a request. RL trainers use it for MoE routing replay (R3): the training forward pass reuses the rollout's routing.
+
+```bash
+vllm serve Qwen/Qwen3-30B-A3B --enable-return-routed-experts
+# offline: LLM("Qwen/Qwen3-30B-A3B", enable_return_routed_experts=True)
+```
+
+The flag sets `AuxOutputConfig.enable_return_routed_experts` (full form: `--aux-output-config '{"enable_return_routed_experts": true, "max_bytes": N}'`). There is no per-request on/off switch.
+
+## Requirements
+
+Startup fails with a `ValueError` unless:
+
+- **Model Runner V2** is used (`VLLM_USE_V2_MODEL_RUNNER=1` if vLLM falls back to V1);
+- the runner is `generate` and the model is **MoE**;
+- **prefix caching is enabled** (the default). `--no-enable-prefix-caching` fails; the old v0.21 advice to disable it is wrong.
+
+Rejected at startup: adaptive speculative verification, PP > 1, DCP/PCP > 1, and the `NixlConnector`, `NixlPullConnector`, `NixlPushConnector`, `MoRIIOConnector`, `MooncakeConnector` KV connectors. Regular speculative decoding works.
+
+### How it works: aux output connector
+
+Routing is stored by the aux output connector (`vllm/distributed/aux_output_connector/`, configured via `--aux-output-config`), keyed by KV block hash and shared with prefix caching, which is why prefix caching is required. `max_bytes` is its host-memory LRU capacity (default: derived from KV cache capacity). If a prefix-cache hit needs evicted rows, the worker raises `BlockObjectStoreError`; increase `max_bytes`.
+
+## Output format
+
+| API | Field |
+| --- | --- |
+| Offline (`LLM`, `AsyncLLM`) | `CompletionOutput.routed_experts`: `np.ndarray` or `None` |
+| `/v1/completions`, `/v1/chat/completions` | `choices[i].routed_experts`: base64 `.npy`, **non-streaming only** |
+| `/inference/v1/generate` | `routed_experts` per choice (base64 `.npy`); with `stream: true`, on the final chunk |
+
+- **Shape:** `(num_tokens - 1 - routed_experts_prompt_start, num_moe_layers, num_experts_per_tok)`, `num_tokens` = prompt + output. The last sampled token has no row.
+- **Rows:** row `i` is position `routed_experts_prompt_start + i` of `prompt_token_ids + output_token_ids`.
+- **dtype:** `uint8` for at most 256 experts, else `uint16`; logical expert IDs.
+- Filled only when the request finishes. `None` if the flag is off or the request aborted before any forward pass.
+
+```python
+import base64, io
+import numpy as np
+
+experts = np.load(io.BytesIO(base64.b64decode(choice["routed_experts"])))
+```
+
+## `routed_experts_prompt_start`
+
+Per-request, default `0`: drops the first N prompt-token rows (e.g. routing already received in earlier turns). Must be `0 <= value <= prompt_len`, else HTTP 400. Pass it top-level on `/v1/*completions`, inside `sampling_params` on `/inference/v1/generate`, or as `SamplingParams(routed_experts_prompt_start=...)`.
+
+## Limitations
+
+- The Rust HTTP frontend never returns `routed_experts` and always sends `routed_experts_prompt_start = 0`. Use the Python API server.
+
+Example: [examples/rl/routed_experts_e2e.py](../../examples/rl/routed_experts_e2e.py).
diff --git a/mkdocs.yaml b/mkdocs.yaml
index bed8318998..d591df7b14 100644
--- a/mkdocs.yaml
+++ b/mkdocs.yaml
@@ -106,6 +106,7 @@ plugins:
         examples/features/pause_resume.md: examples/rl/pause_resume.md
         serving/online_serving/decisions.md: models/structured_decisions_models.md
         serving/online_serving/structured_decisions.md: models/structured_decisions_models.md
+        training/routed_experts_replay.md: training/routed_experts.md
 
 markdown_extensions:
   - attr_list