# CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review

arXiv: https://arxiv.org/abs/2506.00296 · HTML: https://mlsanity.com/paper/2506.00296/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2025.

## Built on by (most cited first, 3 of 3)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context](https://mlsanity.com/paper/2601.19494/) (2026)
- [MetaLint: Easy-to-Hard Generalization for Code Linting](https://mlsanity.com/paper/2507.11687/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and RL with AI Feedback (RLAIF), offer trade-offs: RLVR provides reliable feedback for structured tasks like code generation, while RLAIF works for unstructured outputs but is subjective. We bridge this gap with CRScore++, an RL framework that leverages both LLM-based subjective feedback and verifiable signals for training. Extending CRScore, a code review evaluation metric integrating LLMs with verifiers like linters and code smell detectors, CRScore++ transforms these signals into training rewards. We show that CRScore++ improves a weaker student model through a combination of supervised fine-tuning and RL critique from a stronger teacher model, thus enabling generalization to novel programming languages.