Add pipeline tag and library name

README.md

@@ -1,7 +1,11 @@
 ---
-license: apache-2.0
+base_model:
+- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
 language:
 - en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 tags:
 - long-context
 - reinforcement-learning
@@ -9,8 +13,6 @@ tags:
 - rubric-reward
 - qwen3
 - deepseek
-base_model:
-- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
 ---
 
 # LongTraceRL-8B
@@ -20,7 +22,7 @@ base_model:
 
 ## Model Description
 
-**LongTraceRL-8B** is an 8-billion parameter reasoning model trained with reinforcement learning on long-context multi-hop QA tasks using trajectory-based tiered distractors and entity-level rubric rewards.
+**LongTraceRL-8B** is an 8-billion parameter reasoning model trained with reinforcement learning on long-context multi-hop QA tasks using trajectory-based tiered distractors and entity-level rubric rewards. It was introduced in the paper [LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards](https://arxiv.org/abs/2605.31584).
 
 ## Model Details
 
@@ -62,4 +64,4 @@ tokenizer = AutoTokenizer.from_pretrained("THU-KEG/LongTraceRL-8B")
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2605.31584}, 
 }
-```
+```