Research map / Large language models / Agents, code and math
DeepFix: Fixing Common C Language Errors by Deep Learning
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 |
|---|---|---|---|
| iterative repair (5 iterations vs 1) (ablation) | DeepFix · Raw student C programs | remaining error messages: 12296 -> 11377 | Helped |
| longer required fix (>15 vs <10 tokens) | DeepFix · Seeded C programs | fix accuracy: 72.43% -> 50.63% | Hurt |
| evaluate on real errors instead of synthetic seeded errors | DeepFix · C programs | completely fixed programs: 56% -> 27% | Hurt |
| use beam search top-5 ranked lines | DeepFix · Seeded C programs | localization accuracy: 78.68% -> 87.50% | Helped |
Closest papers by meaning
- Deep Reinforcement Learning for Syntactic Error Repair in Student Programs (AAAI 2019 · similarity 0.87)
- Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization (AAAI 2025 · similarity 0.82)
- kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution (NeurIPS 2024 · similarity 0.81)
- AuPair: Golden Example Pairs for Code Repair (ICML 2025 · similarity 0.81)
- LILO: Learning Interpretable Libraries by Compressing and Documenting Code (ICLR 2024 · similarity 0.80)
- Guess & Sketch: Language Model Guided Transpilation (ICLR 2024 · similarity 0.80)
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.