Gen-Verse/CURE

[NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

33
/ 100
Emerging

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.

AI/ML engineering LLM fine-tuning code generation unit test generation reinforcement learning
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 7 / 25
Community 14 / 25

How are scores calculated?

Stars

159

Forks

17

Language

Python

License

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.