Add essential metadata and improve links in model card

This PR adds crucial metadata to the model card, including the `pipeline_tag`, `library_name`, and `license`. These additions enhance the model's discoverability on the Hugging Face Hub, allowing users to easily find it via relevant filters.

Additionally, this PR corrects a broken Hugging Face link in the model card content, ensuring users are directed to the correct Hugging Face collection page.

README.md

@@ -1,3 +1,9 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+---
+
 # ⚛️ Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward
 
 <p align="center">
@@ -77,7 +83,7 @@ We demonstrate through extensive experiments that Atom-Searcher sets a new state
   - 📈 It achieves significant performance gains over strong baselines like **DeepResearcher** and **R1-Searcher** on seven distinct benchmarks.
   - 🧠 At test time, Atom-Searcher **scales its computation effectively**, generating 3.2x more tokens and making 1.24x more tool calls on average than the SOTA baseline, indicating deeper exploration and reasoning without explicit incentives.
 
-👉[Hugging Face Model](https://www.google.com/search?q=https://huggingface.co/collections/ant-group/atom-searcher)
+👉[Hugging Face Collection](https://huggingface.co/collections/ant-group/atom-searcher)
 
 -----