AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

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

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

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 allocation problem and propose When2Think, a post-training framework for hybrid reasoning that dynamically allocates computation based on problem difficulty. Our method introduces

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.