Papers with Code 아카이브

Code Repair

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

2

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/bigcode-project/bigcode-evaluation-harness

공식 코드

OctoPack: Instruction Tuning Code Large Language Models

https://github.com/bigcode-project/octopack

공식 코드

OctoPack: Instruction Tuning Code Large Language Models

https://github.com/bin123apple/autocoder

공식 코드

AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}

https://github.com/hpc-fortran2cpp/fortran2cpp

공식 코드

Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration

https://github.com/kevincl16/dsdbench

공식 코드

Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors

https://github.com/logic-star-ai/swt-bench

공식 코드

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents

https://github.com/madaan/pie-perf

공식 코드

Learning Performance-Improving Code Edits

https://github.com/michiyasunaga/bifi

공식 코드

Break-It-Fix-It: Unsupervised Learning for Program Repair

https://github.com/microsoft/CodeXGLUE

공식 코드

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/microsoft/monitors4codegen

공식 코드

Guiding Language Models of Code with Global Context using Monitors

https://github.com/neuir/coast

공식 코드

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

https://github.com/neuir/intervenor

공식 코드

INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair

https://github.com/nvlabs/craftrtl

공식 코드

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair

https://github.com/oppo-personalai/agent-kb

공식 코드

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

https://github.com/purushottamkar/macer

공식 코드

MACER: A Modular Framework for Accelerated Compilation Error Repair

https://github.com/Avmb/semantic_neq_game

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/Mind23-2/MindCode-134

Learning Performance-Improving Code Edits

https://github.com/deeplearnxmu/unigencoder

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/facebookresearch/CodeGen

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/infi-coder/infibench-evaluation-harness

OctoPack: Instruction Tuning Code Large Language Models

https://github.com/kilimanj4r0/code-summarization-beyond-function-level

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/sberbank-ai/fusion_brain_aij2021

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/yueyuel/programgen-lms-reliability

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.