ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
For the AI peer review community, this work addresses the problem of shallow LLM-generated reviews by introducing a practical framework that improves substantiveness, though the gains are incremental over existing LLM-based approaches.
LLM-based peer reviewers often produce superficial feedback. The authors propose ReviewGrounder, a multi-agent framework that uses rubrics and tool-integrated evidence grounding, achieving better review quality than GPT-4.1 and DeepSeek-R1-670B on their ReviewBench benchmark across 8 dimensions.
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}.