AI RESEARCH
MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
arXiv CS.AI
•
ArXi:2604.14564v1 Announce Type: new Reinforcement learning (RL) paradigms have nstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains the achievable performance ceiling. Search-enhanced RL alleviates this issue by