**When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reas

**When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models**

> Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing approaches based on uniform length penalties or rigid routing incur an efficiency tax, trading reduced computation on easy instances for accuracy loss on hard instances. We formulate efficient reasoning as an instance-adaptive computation...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：ai-models
- **发布时间**：2026-09-18 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.19671)