Dongfei Cui

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS

2025 · arXiv (Cornell University)

Test-time scaling has emerged as a promising paradigm in language modeling, leveraging additional computational resources at inference time to enhance model performance. In this work, we introduce R2-LLMs, a novel and versatile hierarchical retrieval-augmented reasoning …