Qwen前核心负责人亲自复盘Qwen3设计缺陷，解释了为什么团队转向智能体RL路径，技术干货满满。
林俊扬（前Qwen技术负责人）指出Qwen3的混合思考模式存在不足，动态思考预算机制并未有效融合推理与行动。他主张应从推理思考转向智能体思考，并强调智能体强化学习（agentic RL）的基础设施构建比预训练RL更难。他警告奖励破解（reward hacking）在智能体训练中更具危害性，需设计更稳健的奖励模型。
Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents
Junyang Lin, the former technical lead of Alibaba's Qwen, walked through the model family in a talk "towards a generalist model / agent," then expanded it in an essay. We read both for practitioners: Qwen3 hybrid thinking modes and dynamic thinking budgets, where the merge fell short, the shift from reasoning thinking to agentic thinking, why agentic RL infrastructure is harder, and where reward hacking bites. The post Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents appeared first on MarkTechPost .