Research map / Large language models / Agents, code and math
Automatic Code Review by Learning the Revision of Source Code
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add PAE revision feature extraction to LSCNN (ablation) | DACE · Apache code review average | F1: 0.370 -> 0.482 | Helped |
| add PAE revision feature extraction to LSCNN (ablation) | DACE · Apache code review average | AUC: 0.777 -> 0.828 | Helped |
| add CNN-LSTM context enrichment to PAE (ablation) | DACE · Apache code review average | F1: 0.438 -> 0.482 | Helped |
| add CNN-LSTM context enrichment to PAE (ablation) | DACE · Apache code review average | AUC: 0.814 -> 0.828 | Helped |
| add CNN-LSTM context enrichment to PAE (ablation) | DACE · aurora and hbase-git | F1: aurora 0.571 -> 0.403; hbase-git 0.411 -> 0.396 | Mixed |
Closest papers by meaning
- Towards Practical Defect-Focused Automated Code Review (ICML 2025 · similarity 0.83)
- RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing (ICML 2025 · similarity 0.80)
- RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph (ICLR 2025 · similarity 0.80)
- Unsupervised Evaluation of Code LLMs with Round-Trip Correctness (ICML 2024 · similarity 0.80)
- Bridging the Gap between Source Code and Requirements Using GPT (Student Abstract) (AAAI 2024 · similarity 0.79)
- Less Is More: Adaptive Program Repair with Bug Localization and Preference Learning (AAAI 2025 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.