elvis@omarsar0 · X该研究指出，在自我改进的AI智能体中，“更强模型总能写出更好进化器提示词”的直觉是错误的。工作区分了两种能力：产生更新的能力在不同模型间趋于平坦，而从更新中受益的能力呈倒U形曲线，在中等模型处达到顶峰。弱模型无法有效激活更新，强模型则因已处性能高位而获益甚微。因此，成本效益最佳的配置是：使用廉价的中等模型担任“进化器”，而将昂贵的强模型用作“求解器”。
Very good advice on self-improving agents.
（bookmark it）
This is something I am seeing in my own experiments with coding agents and harnesses for long-horizon tasks.
What I have found is that stronger models do not always evolve better agents.
The current believe in self-evolving agents is that a bigger model writes better prompt and skill edits， so devs put their best model in the evolver seat.
New research shows that intuition is mostly wrong.
The work separates two abilities that usually get conflated. Producing harness updates stays flat across model capability， so Qwen3.5-9B writes edits roughly as good as Claude Opus 4.6. Benefiting from those updates follows an inverted-U that peaks at mid-tier models， while weak models fail to even activate the edits and strong models have little headroom left.