Update README.md

README.md

@@ -1,17 +1,18 @@
 ---
 license: mit
 ---
-**SWE-Dev-9B is trained from [glm-4-9B-chat](https://huggingface.co/THUDM/glm-4-9b-chat/)**
 
-🚀 SWE-Dev, a groundbreaking open-source Software Engineering Agent (SWE Agent)!
+🚀 SWE-Dev, an open-source Agent for Software Engineering tasks!
 
-📚 We have built a high-quality dataset and significantly improved the model’s performance on SWE tasks through rejection sampling. We also explored the feasibility of various offline algorithms on SWE through extensive experiments.
+💡 We develop a comprehensive pipeline for creating developer-oriented datasets from GitHub repositories, including issue tracking, code localization, test case generation, and evaluation.
 
-🔧 Using only open-source frameworks and models, SWE-Dev-7B and 32B achieved solve rates of 23.4% and 36.6% on SWE-bench-Verified, respectively, even approaching the performance of closed-source models like GPT-4o.
+🔧 Based on open-source frameworks (OpenHands) and models, SWE-Dev-7B and 32B achieved solve rates of 23.4% and 36.6% on SWE-bench-Verified, respectively, even approaching the performance of GPT-4o. 
 
-🛠 No need for complex prompt engineering or expensive multi-round evaluations—performance breakthroughs can be achieved with simplified inference scaling! We discovered that increasing interaction rounds significantly boosts model performance. For instance, DeepSeek-V3’s solve rate improved from 37.4% at 30 rounds to 41.2% at 75 rounds. Context extension also proved highly effective for short-text-trained models!
+📚 We find that training data scaling and inference scaling can both effectively boost the performance of models on SWE-bench. Moreover, higher data quality further improves this trend when combined with reinforcement fine-tuning (RFT). For inference scaling specifically, the solve rate on SWE-Dev increased from 34.0% at 30 rounds to 36.6% at 75 rounds.
+
+
+SWE-Dev-9B is trained from [glm-4-9B-chat](https://huggingface.co/THUDM/glm-4-9b-chat/)
 
-💡 We further explored the scaling laws between data size, interaction rounds, and model performance, demonstrating that smaller, high-quality datasets are sufficient to support top-tier performance.
 
 Notion Link: https://ubecwang.notion.site/1bc32cf963e080b2a01df2895f66021f?v=1bc32cf963e0810ca07e000c86c4c1e1