diff --git a/BENCHMARK_WORKFLOW.md b/BENCHMARK_WORKFLOW.md
index 6a2f352..0553597 100644
--- a/BENCHMARK_WORKFLOW.md
+++ b/BENCHMARK_WORKFLOW.md
@@ -79,6 +79,11 @@
    - Scripts load the platform file via `scripts/common/platform.sh`; the active platform is selected by the `PLATFORM` env var or auto-detected.
    - Keep experiment scripts free of hardcoded device IDs, image names, or model root paths.
 
+9. **Record the exact server launch command/args for every run.**
+   - The exact command or full argument list used to start the server must be saved in `results.json` under `config.server_args` (or `config.phaseN_server_args` if the experiment starts the server in multiple phases).
+   - This is required for cross-platform reproduction: when the same experiment is run on H200 and P800, the only differences should be model paths, ports, and device IDs.
+   - If an experiment uses `start_server.sh`, that script should be self-contained and its command line should be reproducible from `results.json` alone.
+
 ## Naming Conventions
 
 ### Experiment result directories
@@ -164,7 +169,8 @@ The JSON file inside each `bench_results/<run>/` directory should follow a stabl
     "spec_tokens": 5,
     "block_size": 256,
     "max_num_seqs": 256,
-    "extra_args": "--no-disable-hybrid-kv-cache-manager"
+    "extra_args": "--no-disable-hybrid-kv-cache-manager",
+    "server_args": "vllm serve /data/models/DeepSeek-V4-Flash-DSpark --trust-remote-code --tensor-parallel-size 8 --kv-cache-dtype fp8 --max-model-len auto --max-num-seqs 256 --spec-method dspark --spec-tokens 5 --no-disable-hybrid-kv-cache-manager --port 30004"
   },
   "scenarios": [
     {
@@ -297,8 +303,9 @@ At minimum, `run_bench.sh` should:
 2. Read `config.env`.
 3. Create `experiments/<name>/results/<RUN_ID>/`.
 4. Call `write_metadata_json` to create `results.json`.
-5. Run the benchmark scenarios.
-6. Call `parse_results.py` to generate `report.md`.
+5. Record the exact server launch command/args in `results.json` `config.server_args` (or `phaseN_server_args`).
+6. Run the benchmark scenarios.
+7. Call `parse_results.py` to generate `report.md`.
 
 ### 3. Reuse shared helpers
 
@@ -325,6 +332,7 @@ See `docs/H200_QUICKSTART.md` for a concrete H200 porting walkthrough.
 - [ ] `<run>/report.md` (or equivalent human-readable `.md`) exists.
 - [ ] `<run>/results.json` exists and follows the [Final JSON Schema](#final-json-schema).
 - [ ] `<run>/results.json` metadata records the `chip`/`accelerator` and `engine`/`backend` used.
+- [ ] `<run>/results.json` `config` records the exact server launch command/args (`server_args` or `phaseN_server_args`).
 - [ ] Raw output filenames include the chip/accelerator and engine when cross-platform runs may collide.
 - [ ] `<run>/README.md` exists and documents provenance (or the report itself covers provenance).
 - [ ] Scripts either live under `experiments/<name>/` or in `scripts/` (or `scripts/<group>/`).