InternReviewer&InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
This work presents a comprehensive framework for the development and evaluation of specialized scholarly agents, InternReviewer and InternAdvocate, by implementing an agentic Reinforcement Learning (RL) paradigm driven by a unified objective metric and reward system.
Xuerui Su, Liya Guo, Qizhi Pei et al.
· 0 citations