Cooolder
/

SCOPE

@@ -18,7 +18,7 @@ SCOPE reframes model routing as a pre-hoc estimation problem: instead of directl
 Overall, SCOPE provides a scalable, explainable, and controllable solution for allocating test-time compute across heterogeneous model portfolios.
 <p align="center">
-  <img src="assets/1.png" width="800">
 </p>
 The figure above illustrates the core difference between traditional routers and SCOPE.
 Conventional LLM routers treat routing as a closed-set classification problem, simply memorizing model names and selecting one model per query. In contrast, SCOPE reasons over models’ past behaviors, explicitly predicting outcome correctness and token cost, and then makes a budget-aware decision based on these estimates. This design allows SCOPE to generalize to unseen models and supports dynamic cost–accuracy control at inference time.

 Overall, SCOPE provides a scalable, explainable, and controllable solution for allocating test-time compute across heterogeneous model portfolios.
 <p align="center">
+  <img src="assets/1.png" width="500">
 </p>
 The figure above illustrates the core difference between traditional routers and SCOPE.
 Conventional LLM routers treat routing as a closed-set classification problem, simply memorizing model names and selecting one model per query. In contrast, SCOPE reasons over models’ past behaviors, explicitly predicting outcome correctness and token cost, and then makes a budget-aware decision based on these estimates. This design allows SCOPE to generalize to unseen models and supports dynamic cost–accuracy control at inference time.