AI RESEARCH
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
arXiv CS.LG
•
ArXi:2601.07208v2 Announce Type: replace Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain settings remains a critical challenge, as unconstrained generation entails multi-faceted and often conflicting objectives - such as creativity versus factuality - where rigid, static reward scalarization is inherently suboptimal.