基于阿里最新开源的Qwen3-32B模型，DeepSWE开源AI Agent登顶榜首

Core Insights - Together.ai and Agentica have launched an innovative AI Agent framework called DeepSWE, based on Alibaba's latest open-source Qwen3-32B model [1] - DeepSWE has been trained entirely using reinforcement learning, showcasing its effectiveness and potential in the AI landscape [1] - In SWE-Bench-Verified tests, DeepSWE achieved an average Pass@1 accuracy of 42.2% over 16 runs, with performance further enhanced to 59% using mixed testing [1] - DeepSWE outperforms all other open-source agent frameworks, demonstrating superior performance without relying on stronger proprietary teacher models for distillation or SFT [1]