RubricReviewer: From Direct Critique to Rubric-Driven Review via Agentic Evidence Synthesis and Human-Aligned Generation
Organizations: Shandong University · Huawei Technologies Co., Ltd.
Abstract
Peer review at major venues is under unprecedented submission pressure, motivating the use of large language models (LLMs) as review assistants. Existing LLM-based reviewers, however, face two structural limitations. First, they map manuscripts directly to reviews, leaving the underlying rubric implicit and entangling its derivation with the judgement. Second, the prevailing paradigms each capture only half of a good review: training-free agents gather broad evidence but produce undirected critiques, while training-based reviewers inherit human discriminative judgement together with its noise and uneven coverage. We introduce RubricReviewer, a fully rubric-driven framework that addresses both limitations. It makes rubric generation an explicit intermediate step, so that both review generation and the final assessment are conditioned on paper-adaptive rubrics. It further combines a training-free agent (Scout) that gathers external evidence with a human-aligned trained model (Aligner) that consumes this evidence, fusing the strengths of both supervision sources. Experiments on real-world submissions show that RubricReviewer produces reviews that are markedly more comprehensive and more discriminative than prior systems, and exhibits the strongest robustness against adversarial prompt-injection attacks. Ablation studies further confirm the necessity of each component.
Figures & tables
| Rubric Generation | Review Generation | ||||||
| Method | Backbone | #R/paper | Recall | R-Lenient | R-Strict | ||
| Foundation LLMs (zero-shot) | |||||||
| GPT-5.2 | – | 10.4 | 34.3 | 4.2 | 20.0 | 14.6 | 34.5 |
| Training-free Agentic Frameworks | |||||||
| AI Scientist | GPT-5.2 | 11.3 | 38.4 | 9.0 | 31.7 | 22.5 | 11.1 |
| AgentReview | GPT-5.2 | 13.5 | 45.2 | 5.2 | 35.3 | 24.7 | 6.0 |
| Method | MSE | MAE | ACC |
| Foundation LLMs (zero-shot) | |||
| GPT-5.2 | 1.475 | 0.905 | 54.0 |
| Training-free Agentic Frameworks | |||
| AI Scientist | 5.805 | 2.085 | 66.5 |
| AgentReview | 1.998 | 1.065 | 34.5 |
| DeepReviewer 2.0 | 1.490 | 0.935 | 41.5 |
| Variant | Recall | R-Lenient | R-Strict |
| Ours (full) | 80.5 | 61.4 | 38.4 |
| Rubric stage | |||
| general rubrics | 25.1 ↓55.4 | – | – |
| model-generated rubrics | 78.6 ↓1.9 | – | – |
| cite-derived rubrics | 78.8 ↓1.7 | – | – |
| Scout reference | 80.1 ↓0.4 | – | – |
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
| Category | # Rubrics | ID range |
| Idea & Methodology | 14 | G1–G14 |
| Experiment & Evaluation | 18 | E1–E18 |
| Presentation & Writing | 8 | P1–P8 |
| Total | 40 | — |
Automated Peer Review
Automated peer review uses computational systems, especially language models, to assess research papers, generate feedback, and support editorial decisions.
See all 121 papers