砍掉后 12 层，3B 决策模型 RSI-Jev 超过 4B 模型
作者发现决策不需要完整 LLM 深度，Qwen3.5-4B 截到第 20 层性能几乎不变，据此发布 RSI-Jev v5.0-VL 3B。
A System One model may not need the full depth of an LLM. AutoScientists found that much of the later network can be removed without hurting decision performance. On Qwen3.5-4B, stopping at layer 20 of 32 performed basically the same as using the full model. So they cut the last 12 layers and shipped RSI-Jev v5.0-VL 3B. On Decision Index, it scores 38.38 vs 28.97 for the next best model at 3B and below, and it also beats eleven 4B models. In hindsight, this kind of makes sense: deciding and speaking are different jobs. A System One model doesn’t need to generate the next word. It just needs to read and make a call. The next question is even more interesting: why should every question use the same depth? If easy ones can stop early while hard ones go deeper, this could get a lot faster. https://github.com/Shanghua-Gao/RSI-Jev
这条是引用着另一条写的：x.com/gaoshanghua/status/2103572751466312150