3 papers
cs.LG2026
ExpRL: Exploratory RL for LLM Mid-Training
Violet Xiang, Amrith Setlur, Chase Blagden +2
Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In p…
cs.CL2025
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
Yinlam Chow, Guy Tennenholtz, Izzeddin Gur +7
Recent studies have indicated that effectively utilizing inference-time compute is crucial for attaining better performance from large language models (LLMs). In this work, we prop…
cs.LG2025
Generative Verifiers: Reward Modeling as Next-Token Prediction
Lunjun Zhang, Arian Hosseini, Hritik Bansal +3
Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs). A common approach is the Best-of-N method, where N candidate solutio…