10 papers
OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review
Zhengfeng Li, Lei Zhang, Xianwei Wu +8
LLM-based code review agents promise scalable, always-on review, yet current systems suffer from two intertwined weaknesses: (1) non-determinism--unbounded tool use makes review ou…
Improving LLM-Based Go Code Review through Issue-List Generation and Context Augmentation
Kexin Sun, Yucong Guan, Jiaqi Sun +6
LLMs have shown strong potential for automating code review, yet their practical utility depends heavily on the design of generation and context strategies. In this paper, we inves…
Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions
Kexin Sun, Hongyu Kuang, Sebastian Baltes +6
AI-based code review tools automatically review and comment on pull requests to improve code quality. Despite their growing presence, little is known about their actual impact. We…
ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling
Yongda Yu, Lei Zhang, Xinxin Guo +9
In many applications involving intelligent agents, the overwhelming volume of alerts (mostly false) generated by the agents may desensitize users and cause them to overlook critica…
AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context
Lei Zhang, Yongda Yu, Minghui Yu +11
High-quality evaluation benchmarks are pivotal for deploying Large Language Models (LLMs) in Automated Code Review (ACR). However, existing benchmarks suffer from two critical limi…
Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach
Yongda Yu, Guohao Shi, Xianwei Wu +8
Large Language Models (LLMs) have shown great potential in supporting automated code review due to their impressive capabilities in context understanding and reasoning. However, th…