activity
20242026
collaborators

13 papers

cs.CL2026

Stabilizing Efficient Reasoning with Step-Level Advantage Selection

Han Wang, Xiaodong Yu, Jialian Wu +4

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While…

cs.AI2026

DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains

Tian Liang, Wenxiang Jiao, Zhiwei He +3

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex one…

cs.CL2025

Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation

Ziyin Zhang, Jiahao Xu, Tian Liang +4

Conventional speculative decoding (SD) methods utilize a predefined length policy for proposing drafts, which implies the premise that the target model smoothly accepts the propose…

cs.CL2025

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

Ziyin Zhang, Jiahao Xu, Zhiwei He +10

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approache…

cs.AI2025

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

Mengru Wang, Xingyu Chen, Yue Wang +12

Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structur…

cs.CL2025

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Zhiwei He, Tian Liang, Jiahao Xu +12

Reinforcement learning (RL) with large language models shows promise in complex reasoning. However, its progress is hindered by the lack of large-scale training data that is suffic…