mlsanityData to 14 Oct 2026

Automated Code Review Using Large Language Models with Symbolic Reasoning

arXiv 2507.18476 ↗First posted 24 Jul 2025cs.SE cs.AIcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Code review is one of the key processes in the software development lifecycle and is essential to maintain code quality. However, manual code review is subjective and time consuming. Given its rule-based nature, code review is well suited for automation. In recent years, significant efforts have been made to automate this process with the help of artificial intelligence. Recent developments in Large Language Models (LLMs) have also emerged as a promising tool in this area, but these models often lack the logical reasoning capabilities needed to fully understand and evaluate code. To overcome this limitation, this study proposes a hybrid approach that integrates symbolic reasoning techniques with LLMs to automate the code review process. We tested our approach using the CodexGlue dataset, comparing several models, including CodeT5, CodeBERT, and GraphCodeBERT, to assess the effectiveness of combining symbolic reasoning and prompting techniques with LLMs. Our results show that this approach improves the accuracy and efficiency of automated code review.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 12 of its 33 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

12 of 33 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  5. 2017Mixed Precision Trainingcited by 1,156
  6. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  7. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
  8. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
  9. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 221
  10. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  11. 2024Fine-Tuning and Prompt Engineering for Large Language Models-based Code Review Automationcited by 23
  12. 2023On the Reliability and Explainability of Language Models for Program Generationcited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024CodeMind: Evaluating Large Language Models for Code Reasoning
  2. 2025Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach
  3. 2025LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead ↗
  4. 2025From Code to Courtroom: LLMs as the New Software Judges
  5. 2024The Potential of LLMs in Automating Software Testing: From Generation to Reporting
  6. 2025Rethinking Code Review Workflows with LLM Assistance: An Empirical Study
  7. 2024CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
  8. 2026Evaluating LLMs Code Reasoning Under Real-World Context