Tengyao Tu

2 accepted papers

2026

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

Tengyao Tu, Yulin Li, Huiling Zhen, Libo Qin, Zhoujun Wei, Jinghua Piao +3

ICML 2026poster

Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking". Existing methods to mitigate this issue either rely …

Cited by 0 Source ↗Scholar ↗

2026

Efficient Reasoning with Balanced Thinking

Yulin Li, Tengyao Tu, Li Ding, Junjie Wang, Hui-Ling Zhen, Yixin Chen +2

ICLR 2026poster

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 ineffic…

Cited by 0 Source ↗code ↗Scholar ↗