Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents
Qwen's former technical lead just revealed why hybrid thinking failed — and what agents need to succeed.
Why it matters
Strategic technical commentary from a major model lab's ex-leadership on reasoning paradigm shifts and infrastructure challenges. Practitioners and builders need to understand why agentic RL is harder and where reasoning-first approaches stumbled.
The key facts
6 to knowJunyang Lin (former Qwen technical lead) published analysis on hybrid thinking limitations
Key topic: dynamic thinking budgets and where the merge approach fell short
Strategic shift: from reasoning-first thinking to agentic thinking paradigm
Infrastructure challenge identified: agentic RL is harder to implement than reasoning-focused systems
Technical risk flagged: reward hacking vulnerabilities in agentic training
Format: talk + published essay for practitioner audience
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: 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…