#artificial intelligence
Feb 2026
To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
The RLVR across domains exhibits small mutual interferences, and reasoning-intensive domains have mutually synergistic effects, and the internal mechanisms from the perspectives of information constraints, model prediction behavior and self-verification are analyzed.
Haoqing Wang, Xiang Long, Ziheng Li et al.
· arXiv.org · 11 citations