zjunlp/ReCode
[AAAI 2026] ReCode: Reinforced Code Knowledge Editing for API Updates
This project helps large language models (LLMs) update their understanding of how to use external software libraries when those libraries change. It takes an LLM's current code generation capabilities and information about API updates, then trains the model to produce correct, updated code. This tool is for researchers and developers who work with LLMs and are building code generation tools, especially those that interact with rapidly evolving external libraries.
No commits in the last 6 months.
Use this if your large language model struggles to generate accurate code for libraries that have undergone API changes, even when provided with current documentation.
Not ideal if you are looking for a tool to manually update your existing codebase or an API migration assistant that doesn't involve training an LLM.
Stars
24
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jul 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/ReCode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MMMU-Benchmark/MMMU
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal...
pat-jj/DeepRetrieval
[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome
lupantech/MathVista
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
x66ccff/liveideabench
[𝐍𝐚𝐭𝐮𝐫𝐞 𝐂𝐨𝐦𝐦𝐮𝐧𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬] 🤖💡 LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea...
ise-uiuc/magicoder
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct