Update README.md

README.md

@@ -16,7 +16,7 @@ base_model:
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6665dd2b3a64c70529f7542c/8o-IE7N3GwSFCIH3ntc8E.png)
 
-📖 [Technical Report](https://huggingface.co/Skywork/Skywork-SWE-32B/resolve/main/assets/Report.pdf)   |   📰 [Blog](https://quixotic-sting-239.notion.site/eb17f379610040ceb54da5d5d24065bd)
+📖 [Technical Report](https://www.arxiv.org/pdf/2506.19290)   |   📰 [Blog](https://quixotic-sting-239.notion.site/eb17f379610040ceb54da5d5d24065bd)
 
 ## Model Introduction
 ***Skywork-SWE-32B*** is a code agent model developed by [Skywork AI](https://skywork.ai/home), specifically designed for software engineering (SWE) tasks. It demonstrates strong performance across several key metrics:
@@ -29,7 +29,7 @@ We also introduce an efficient and automated pipeline for SWE data collection, c
 
 | Model Name | Backbone LLM | HuggingFace Link | Technical Report | Blog |
 |---|---------------|-----------|-|-|
-|Skywork-SWE-32B | [🤗 Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) | [🤗 Skywork-SWE-32B](https://huggingface.co/Skywork/Skywork-SWE-32B) | [Technical Report](https://huggingface.co/Skywork/Skywork-SWE-32B/resolve/main/assets/Report.pdf) | [Blog](https://quixotic-sting-239.notion.site/eb17f379610040ceb54da5d5d24065bd)|
+|Skywork-SWE-32B | [🤗 Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) | [🤗 Skywork-SWE-32B](https://huggingface.co/Skywork/Skywork-SWE-32B) | [Technical Report](https://www.arxiv.org/pdf/2506.19290) | [Blog](https://quixotic-sting-239.notion.site/eb17f379610040ceb54da5d5d24065bd)|
 
 ## Evaluation