ReviewRL combines arXiv retrieval, supervised fine-tuning, and reinforcement learning with a composite reward to generate paper reviews that better match human ratings and judged quality.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReviewRL: Towards Automated Scientific Review with RL
ReviewRL combines arXiv retrieval, supervised fine-tuning, and reinforcement learning with a composite reward to generate paper reviews that better match human ratings and judged quality.