LLM agents dynamically exploring repositories via bash commands achieve competitive accuracy to context-provided LLMs across four classification tasks, with superior robustness to artifact size.
Evaluating large language models for code review
4 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.SE 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
Reviewer bots' higher comment volume on AI agent PRs is associated with slower resolutions and poorer average feedback quality, while feedback quality itself has no association with PR outcomes.
Automated LLM-based evaluation of code review bot comments achieves only moderate agreement (0.44-0.62) with developer labels in an industrial dataset because developer decisions reflect contextual constraints beyond comment quality.
SmartPatchLinker is an open-source Chrome extension that detects and ranks semantically linked patches directly in the Gerrit code review workflow.
citing papers explorer
-
Agentic Repository Mining: A Multi-Task Evaluation
LLM agents dynamically exploring repositories via bash commands achieve competitive accuracy to context-provided LLMs across four classification tasks, with superior robustness to artifact size.
-
On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories
Reviewer bots' higher comment volume on AI agent PRs is associated with slower resolutions and poorer average feedback quality, while feedback quality itself has no association with PR outcomes.
-
Understanding the Limits of Automated Evaluation for Code Review Bots in Practice
Automated LLM-based evaluation of code review bot comments achieves only moderate agreement (0.44-0.62) with developer labels in an industrial dataset because developer decisions reflect contextual constraints beyond comment quality.
-
SmartPatchLinker: An Open-Source Tool to Linked Changes Detection for Code Review
SmartPatchLinker is an open-source Chrome extension that detects and ranks semantically linked patches directly in the Gerrit code review workflow.