Gen-Verse/CURE
[NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
This project helps developers improve how large language models (LLMs) write and test code. It takes existing LLM code models and coding problem datasets as input, then co-evolves the LLM's coding and unit testing abilities using reinforcement learning. The output is a more accurate and efficient LLM coder that can also generate better unit tests, aimed at AI/ML engineers and researchers working on code generation.
159 stars. No commits in the last 6 months.
Use this if you are an AI/ML engineer or researcher looking to enhance the code generation and testing capabilities of your large language models, especially when working with competitive programming or similar coding challenges.
Not ideal if you are an application developer simply looking for an LLM to generate code without wanting to fine-tune or train the underlying models.
Stars
159
Forks
17
Language
Python
License
—
Category
Last pushed
Sep 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/Gen-Verse/CURE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
k4black/codebleu
Pip compatible CodeBLEU metric implementation available for linux/macos/win
LiveCodeBench/LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of...
EdinburghNLP/code-docstring-corpus
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and...
hendrycks/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
solis-team/Hydra
[FSE 2026] Do Not Treat Code as Natural Language: Implications for Repository-Level Code...