Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks
| Date | Stars |
|---|---|
| 2026-07-31 | 533 |
| 2026-08-05 | 533 |
| 2026-08-06 | 533 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# CGM: Code Graph LLM  ## Contents - [News](#news) - [Introduction](#introduction) - [Installation](#installation) - [Examples](#examples) - [Rewriter](#rewriter) - [Retriever](#retriever) - [Reranker](#reranker) - [Reader](#reader) - [Contributing](#contributing) - [Citation](#citation) - [Join Us](#join-us) ## News 🔥🔥🔥 [2025/09/19] Our paper [Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks](https://arxiv.org/abs/2505.16901) has been accepted to NeurIPS 2025!  🔥🔥🔥 [2025/01/15] We are pleased to announce the updated version of the CGM-72B-V1.2. The model further achieves a remarkable 44.00% resolve rate on the SWE-Bench-Lite leaderboard. 🔥🔥🔥 [2024/12/28] We are pleased to announce the updated version of the CGM-72B-V1.1. The model further achieves a remarkable 41.67% resolve rate on the SWE-Bench-Lite leaderboard. 🔥🔥🔥 [2024/10/28] We are pleased to announce that CGM-72B achieves a remarkable 35.67% resolve rate on the SWE-Bench-Lite leaderboard. 🔥🔥🔥 [2024/10/28] We released **CGM**, mainly for repository-level coding tasks. - 📜 **Paper**: [Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks](https://arxiv.org/abs/2505.16901) - 🤖 **Model**: [codefuse-ai/CodeFuse-CGM-72B](https://huggingface.co/codefuse-ai/CodeFuse-CGM-72B) - 📊 **Data**: [codefuse-ai/CodeGraph](https://huggingface.co/datasets/codefuse-ai/CodeGraph) ## Introduction We propose a graph-based framework CGM for real-world SE tasks. Before CGM starts its work, we construct a repository-level code graph to better represent the repository context and its structure by Code Graph Generator. Inspired by the Retrieval-Augmented Generation (RAG) approach, CGM framework is designed as a chain structure consisting of four atomic nodes, termed as R4 (Rewriter, Retriever, Reranker, and Reader) chain for this scenario. Given an issue, the initial input to the CGM framework includes the issue description and the corresponding code graph. Rewriter will first rewrite the original issue by extracting keywords and generating relevant queries for code graph. Then a heuristic code subgraph is retrieved through Retriever based on the matching anchor nodes from rewriter output. Given that the resulting subgraph provides a relatively broad context necessary for reference, we need a Reranker to identify the files most likely to be modified as a further hint. Subsequently, both the retrieved subgraph and the identified files are input into a trainable, graph-based Reader to generate the corresponding code patch. ### Framework  ### Highlights :white_check_mark: **Code Graph**: Train models on multiple tasks while maintaining a balance between them. The models can even generalize to new, previously unseen tasks. :white_check_mark: **Multi-framework**: It provides support for both Accelerate (with Deepspeed and FSDP) :white_check_mark: **Efficient fine-tuning**: It supports LoRA, QLoRA as well as Full-parameters training, enabling fine-tuning of large models with minimal resources. The training speed meets the demands of almost all fine-tuning scenarios. ## Installation ### Prerequisites - Python 3.8+ - pip ### Required Packages ```bash transformers==4.46.1 tokenizers==0.20.0 accelerate==1.0.1 peft==0.13.2 jinja2==2.11.3 fuzzywuzzy==0.18.0 python-Levenshtein==0.25.1 networkx==3.0 ``` ## Examples The following chart illustrates the whole processing pipeline of R3.  ### Pre-process for Retriever: Generate Node Embedding Before Retriever, we need to embed - all the nodes in Code Graph into embeddings - Queries generated by Rewriter, into embeddings by [CGE-large](https://huggingface.co/codefuse-ai/CodeFuse-CGE-Large) ```bash python generate_cod
Excerpt of 20,100 characters
Read on GitHub
31
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:271ea9a4b7347d19, llm:Repository description: "[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks" — indicates a framework using LLMs and graph methods for software engineering tasks.
matched fp:271ea9a4b7347d19, llm:Repository description: "[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks" — indicates a framework using LLMs and graph methods for software engineering tasks.
matched fp:271ea9a4b7347d19, llm:Repository description: "[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks" — indicates a framework using LLMs and graph methods for software engineering tasks.