Saved in:
Bibliographic Details
Main Authors: Li, Zhuofeng, Lu, Yi, Jiang, Dongfu, Zhang, Haoxiang, Bai, Yuyang, Li, Chuan, Wang, Yu, Ji, Shuiwang, Xie, Jianwen, Zhang, Yu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.14261
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914476740050944
author Li, Zhuofeng
Lu, Yi
Jiang, Dongfu
Zhang, Haoxiang
Bai, Yuyang
Li, Chuan
Wang, Yu
Ji, Shuiwang
Xie, Jianwen
Zhang, Yu
author_facet Li, Zhuofeng
Lu, Yi
Jiang, Dongfu
Zhang, Haoxiang
Bai, Yuyang
Li, Chuan
Wang, Yu
Ji, Shuiwang
Xie, Jianwen
Zhang, Yu
contents The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic comments lacking substantive, evidence-grounded feedback. We attribute this to the underutilization of two key components of human reviewing: explicit rubrics and contextual grounding in existing work. To address this, we introduce REVIEWBENCH, a benchmark evaluating review text according to paper-specific rubrics derived from official guidelines, the paper's content, and human-written reviews. We further propose REVIEWGROUNDER, a rubric-guided, tool-integrated multi-agent framework that decomposes reviewing into drafting and grounding stages, enriching shallow drafts via targeted evidence consolidation. Experiments on REVIEWBENCH show that REVIEWGROUNDER, using a Phi-4-14B-based drafter and a GPT-OSS-120B-based grounding stage, consistently outperforms baselines with substantially stronger/larger backbones (e.g., GPT-4.1 and DeepSeek-R1-670B) in both alignment with human judgments and rubric-based review quality across 8 dimensions. The code is available \href{https://github.com/EigenTom/ReviewGrounder}{here}.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14261
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
Li, Zhuofeng
Lu, Yi
Jiang, Dongfu
Zhang, Haoxiang
Bai, Yuyang
Li, Chuan
Wang, Yu
Ji, Shuiwang
Xie, Jianwen
Zhang, Yu
Computation and Language
Artificial Intelligence
The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic comments lacking substantive, evidence-grounded feedback. We attribute this to the underutilization of two key components of human reviewing: explicit rubrics and contextual grounding in existing work. To address this, we introduce REVIEWBENCH, a benchmark evaluating review text according to paper-specific rubrics derived from official guidelines, the paper's content, and human-written reviews. We further propose REVIEWGROUNDER, a rubric-guided, tool-integrated multi-agent framework that decomposes reviewing into drafting and grounding stages, enriching shallow drafts via targeted evidence consolidation. Experiments on REVIEWBENCH show that REVIEWGROUNDER, using a Phi-4-14B-based drafter and a GPT-OSS-120B-based grounding stage, consistently outperforms baselines with substantially stronger/larger backbones (e.g., GPT-4.1 and DeepSeek-R1-670B) in both alignment with human judgments and rubric-based review quality across 8 dimensions. The code is available \href{https://github.com/EigenTom/ReviewGrounder}{here}.
title ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.14261