An AI reviewer trained by reinforcement learning to jointly maximize precision and recall of soundness review points outperforms frontier models and other training methods and transfers to other review domains.
As AI conference submissions grow rapidly, AI reviewers are being considered as an alternative. However, simply imitating human reviewing is problematic because reviewing serves multiple purposes, including evaluating papers' soundness, interestingness, and clarity, the last two of which are subjective. In this work, we focus solely on evaluating soundness, the most important and objective criterion, and define the learning objective as jointly maximizing (1) precision, based on the soundness and substantiveness of review points, and (2) recall, the coverage of high-quality reference review points. Under this problem formulation, we construct a quality-labeled review point dataset,…
reinforcement learningprecisionrecallF1 scorelarge language modelsin-domain test setout-of-domain transfer
- Upvotes
- 16
- Authors
- 7
- Published
- Nov 13, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.