Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models
Zongji Yu, Wenshui Luo, Yiliu Sun, Hao Fang, Hanrui Xu, Runmin Cong, Chaochao Lu, Chen Gong
原文摘要
Multi-domain capabilities are critical for practically applicable Large Reasoning Models (LRMs). Therefore, mixed-domain Reinforcement learning (RL) has become a crucial process to jointly train a single LRM with mixed domain data, but it often induces capability trade-offs among different domains. Existing methods attribute this issue to competing cross-domain interactions, and mitigate them by isolating learning directions and balancing learning progress. However, our observation suggests that they also impede supportive knowledge sharing across domains, which make it difficult to match or surpass single-domain performance. To address this problem, we propose \textbf{M}ulti-domain \textbf{C}ontrastive \textbf{P}olicy \textbf{O}ptimization (MCPO), which applies contrastive learning to achieve diverse knowledge sharing and competition. We first localize the interaction units on critical reasoning segments, and then formulate mutually augmented examples to capture both positive and negative interactions. Subsequently, we design complementary contrastive objectives for cross-domain knowledge sharing and intra-domain knowledge consolidation. Overall, we utilize diverse cross-domain interactions to achieve compatibility across domains and discriminability within each domain to form a harmonious reasoning space. Experimental results across a broad range of domains show that MCPO significantly outperforms existing methods mitigating interactions over 3.17 average points, and even surpasses single-domain training over 1.05 average points.
cs.CL