Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanism

Kaixuan Du, Meng Cao, Hang Zhang, Yukun Wang, Xiangzhou Huang, Ni Li

Current label-free RLVR approaches for large language models (LLMs), such as TTRL and Self-reward, have demonstrated effectiveness in improving the performance of LLMs on complex reasoning tasks. However, these methods rely heavily on accurate pseudo-label estimation and converge on spurious yet popular answers, thereby trapping in a dominant mode and limiting further improvements. Building on this, we propose Dual Consensus Reinforcement Learning (DCRL), a novel self-supervised training method which is capable of generating more reliable learning signals through a two-stage consensus mechanism. The model initially acts as an anchor, producing dominant responses; then it serves as an explorer, generating diverse auxiliary signals via a temporary unlearning process. The final training target is derived from the harmonic mean of these two signal sets. Notably, the process operates entirely without external models or supervision. Across eight benchmarks and diverse domains, DCRL consistently improves Pass@1 over majority vote while yielding more stable training dynamics. These results demonstrate that DCRL establishes a scalable path toward stronger reasoning without labels.

• Beihang University
• Beijing Institute of Technology
• Beijing Normal University
• Nankai University
• Tsinghua University
• Zhongguancun Academy
• Beihang University
• Chinese Academy of Sciences
• University of Chinese Academy of Sciences
• Hi-Speed Group
• Beihang University
• Chinese Academy of Sciences
• Langboat
• Beihang University
• European Laboratory for Learning and Intelligent Systems
• IQuest Research
• Renmin University of China
• Shanghai AI Lab
• Shanghai Jiao Tong University
• Sichuan University
• The University of Manchester
• Beihang University
• Renmin University of China
• Tsinghua University
• Beihang University