Update README.md

README.md

@@ -165,6 +165,17 @@ Across all three model sizes and all seven compression ratios, performance on BE
 
 ![kalm-reranker-v1-r2 training](./assets/training.jpg)
 
+#### Potential of test-time compute scaling 
+Results show that this multi-stage strategy largely preserves reranking effectiveness while reducing the estimated online
+computation cost by a factor of several. For example, on BEIR, KaLM-Reranker-V1-Small
+achieves an average nDCG@10 of 61.11 under setting (c), compared with 61.17 under setting (a),
+while reducing the estimated relative serving cost from 8.65x to 2.75x. Interestingly, settings (c)
+and (d) outperform setting (a) on some tasks, suggesting that reranking more candidates at a low
+compression ratio does not necessarily improve reranking quality.
+
+![test-time-compute](./assets/test-time-compute.jpg)
+
+
 ### Acknowledgements
 We sincerely thank `jina-reranker-v3` and `Qwen3-Reranker` for their valuable inspiration and contributions to the reranking community, from which we have learned a lot.