RSI-Jev v6.0-VL: auto-adjusts inference depth by confidence
AutoScientists lets System One models pick low, medium, or high reasoning depth based on their own confidence, raising the 4B Decision Index score from 38.38 to 46.24.
System One models can now adjust their inference effort, not by generating more tokens, but by going deeper through the network. AutoScientists introduced RSI-Jev v6.0-VL, where each decision can use low, medium, or high depth, or choose automatically. The key is confidence awareness. System One models know how sure they are, and AutoScientists designed the auto-effort mechanism around that uncertainty. If the model is confident, it can stop early. If not, it looks deeper. We found that different decisions benefit from different depths: intent and routing are often resolved early, judgement benefits from intermediate depth, while knowledge-intensive and reasoning-heavy decisions benefit from going deeper. On the public Decision Index, v6.0-VL improves the 4B score from 38.38 to 46.24, making it the strongest 4B model there. Take-home: for System One models, thinking harder does not have to mean thinking longer. It can mean using more of the network only when needed. And AutoScientists have already found something better. Code: https://github.com/Shanghua-Gao/RSI-Jev Weights: https://huggingface.co/shgao/rsi-jev-v6.0-vl-4b Effort/depth analysis: https://github.com/Shanghua-Gao/RSI-Jev/blob/main/docs/effort-depth.md
This post quotes another post: “Cutting the last 12 layers lets 3B decision model RSI-Jev beat 4B models”