# Rio 3.5 Open 397B 推出动态推理框架

- 来源：SemiAnalysis (@SemiAnalysis_)
- 发布时间：2026-06-14 04:30
- AIHOT 分数：47
- AIHOT 链接：https://aihot.virxact.com/items/cmqctqbag01risltthowzy4u6
- 原文链接：https://x.com/SemiAnalysis_/status/2065894494935933191

## AI 摘要

情况检测到：里约热内卢市后训练了一个模型。

基于 Qwen 7/2，Rio 3.5 Open 397B 在基础 Qwen 模型之上添加了 SwiReasoning——一个在标准链式推理与隐空间推理之间动态切换的框架，由基于熵的置信信号引导，使模型仅在必要时"出声思考"，其余时间在隐藏空间内静默推理，以提高 token 效率。

## 正文

SITUATION DETECTED： The city of Rio de Janerio has post-trained a model.

Based on Qwen 7/2， Rio 3.5 Open 397B adds SwiReasoning on top of the base Qwen model - a framework that dynamically switches between standard chain-of-thought and latent-space reasoning， guided by entropy-based confidence signals， so the model only "thinks out loud" when it needs to and otherwise reasons silently in hidden space for better token efficiency.