Update README.md

README.md

@@ -337,6 +337,20 @@ if num_funcs >= 4:
 
 ---
 
+## Router Stability (Important)
+
+Dynamic soft‑routing is powerful but sensitive. The training methodology is under active refinement to ensure healthy branch growth without premature specialization.
+
+- Instability: routing entropy can drop early, leading to branch collapse. This is highly sensitive to temperature (τ) scheduling, entropy auxiliary weight (λ), and any warmup forcing.
+- Current safeguards: high initial τ, extended freeze period, entropy‑max regularization, and selective forcing during early steps.
+- Expectations: training curves may show transient oscillations in branch usage while the router and branches co‑adapt.
+- What to monitor: `entropy_norm ≥ 0.75` in the first 3–5k steps; no branch persistently < 15%.
+- Intervention playbook: increase `router_aux_weight`, extend `router_tau_freeze_steps`, temporarily raise `router_tau_start`, or apply targeted forcing to the weakest branch.
+- Fine‑tuning note: if using the standard HF Trainer, consider `router_aux_weight=0` (or use `scripts/train_veronica.py`, which handles entropy‑max correctly).
+- Status: ongoing refinement. Default τ/λ schedules may evolve; core API will remain stable.
+
+---
+
 ## Roadmap
 | Version | Goal |
 |---------|------|