Efficient Reasoning with Balanced Thinking
Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths despite inherent capabilities. These issues lead to inefficiencies and potential inaccuracies, limiting practical deployment in resource-constrained settings. Existing methods to mitigate overthinking, such as suppressing reflective keywords or adjusting reasoning length, may inadvertently induce underthinking, compromising accuracy. Therefore, we propose ReBalance, a training-free framework that achieves efficient reasoning with balanced thinking. ReB...
| Authors | Yulin Li, Tengyao Tu, Li Ding et al. |
|---|---|
| Primary category | cs.AI |
| Published | 12 March 2026 |
| Last updated at source | 2 April 2026 |
Connected in the knowledge graph
- openpangu/openPangu-Embedded-7B-V1.1Model · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.