| title | InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal |
|---|---|
| authors | Xuerui Su, Liya Guo, Qizhi Pei, Qipeng Guo, Zhongbo Tian, Lijun Wu, Kai Chen, Zun Wang |
| date | 2026-07-21 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.28612 |
| affiliation | Shanghai AI Laboratory |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between domain reasoning and factual grounding. This work presents a comprehensive framework for the development and evaluation of specialized scholarly agents, InternReviewer and InternAdvocate. We first establish a large-scale, high-quality scholarly dataset and integrate a high-efficiency arXiv retrieval tool to enable active evidence gathering. To optimize these agents, we implement an agentic Reinforcement Learning (RL) paradigm driven by a unified objective metric and reward system. This system avoids the biases of subjective model-based judging by employing multi-dimensional criteria, including reference-anchored semantic alignment, structural compliance, and a strict verification mechanism that cross-checks citations against real-time interaction logs to eliminate hallucinations. Experimental results demonstrate that agents trained within this closed-loop framework exhibit significant improvements in reasoning depth and citation accuracy. |
cite
@misc{su2026internreviewer,
title={InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal},
author={Xuerui Su and Liya Guo and Qizhi Pei and Qipeng Guo and Zhongbo Tian and Lijun Wu and Kai Chen and Zun Wang},
year={2026},
eprint={2608.28612},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.28612}
}