Breaking Task Isolation: Enhancing Code Review Automation with Mixture-of-Experts Large Language Models

The automation of code review activities has emerged as a critical research focus for optimizing development efficiency while ensuring code quality. While recent advancements in Large Language Models (LLMs) have shown promise, existing approaches predominantly isolate the three core code review task...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings - International Symposium on Software Reliability Engineering s. 227 - 238
Hlavní autoři: Tang, Jiayue, Yang, Li, Yu, Lei, Lu, Junyi, Huang, Zhirong, Zhang, Fengjun, Zuo, Chun
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 21.10.2025
Témata:
Analytical models
Automation
Code Review Automation
Codes
Collaboration
Interference
Large language models
Mixture-of-Experts
Predictive models
Reviews
Routing
Software reliability
ISSN:2332-6549
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The automation of code review activities has emerged as a critical research focus for optimizing development efficiency while ensuring code quality. While recent advancements in Large Language Models (LLMs) have shown promise, existing approaches predominantly isolate the three core code review tasks-review necessity prediction, review comment generation, and code refinement, overlooking their valuable interdependencies. Empirical analysis reveals that isolated-trained comment-generation models often produce superficial comments (e.g., "Undefined 'userInput'") due to insufficient understanding of defect patterns, which is what necessity prediction tasks precisely target. Recent efforts to model interdependencies through knowledge distillation remain constrained by static framework designs.To address these challenges, we present MoE-Reviewer, which adopts the Mixture-of-Experts (MoE) framework on the LLaMA model to tackle the interdependence of code review tasks. MoE-Reviewer enables collaborative modeling for the three tasks mentioned above. By integrating dynamic coordination routing strategies and fine-grained expert mechanisms, MoE-Reviewer facilitates effective knowledge sharing across tasks while mitigating parameter interference. Evaluations conducted on the CodeReviewer dataset demonstrated that MoE-Reviewer outperforms existing methods, achieving state-of-the-art performance with an F1-score of 73.2% and improving the BLEU score for review comment generation by 5.32 to 11.62. Additionally, routing analysis further validates the effectiveness of our approach.
ISSN:2332-6549
DOI:10.1109/ISSRE66568.2025.00033