Update README.md

Nanbeige4.1-3B Report Arxiv

README.md

@@ -33,7 +33,7 @@ Specifically, Nanbeige4.1-3B exhibits the following key strengths:
 * **Robust Preference Alignment:** Nanbeige4.1-3B achieves solid alignment performance, outperforming not only same-scale models such as Qwen3-4B-2507 and Nanbeige4-3B-2511, but also substantially larger models including Qwen3-30B-A3B and Qwen3-32B on Arena-Hard-v2 and Multi-Challenge.
 * **Agentic Capability:** Nanbeige4.1-3B is the first general small model to natively support deep-search tasks and reliably sustain complex problem solving involving more than 500 rounds of tool invocations. It fills a long-standing gap in the small-model ecosystem where models are typically optimized for either general reasoning or agentic scenarios, but rarely excel at both.
   
-> **Technical Report:** [Link](https://huggingface.co/Nanbeige/Nanbeige4.1-3B/blob/main/Nanbeige4.1-3B-Report.pdf)
+> **Technical Report:** [Link](https://arxiv.org/abs/2602.13367)