Code Graph Model (CGM)

Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current solutions predominantly rely on proprietary LLM agents, which introduce unpredictability and limit accessibility, raising concerns about data privacy and model customization. This paper investigates whether open-source ...

🔥🔥🔥 [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 ...
Code Graph Model (CGM)

As shown in Table 4, CGM typically outperforms other RAG methods, regardless of the base model used, suggesting that graph -based context retrieval is more effective for code completion tasks.
Abstract Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current solutions predominantly rely on proprietary LLM agents, which introduce unpredictability and limit accessibility, raising concerns about data privacy and model customization. This paper investigates whether ...

Code Graph Model (CGM)
Abstract Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks re-main challenging. Current solutions predominantly rely on proprietary LLM agents, which introduce unpredictability and limit accessibility, raising concerns about data privacy and model customization. This paper investigates whether ...
Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current solutions predominantly rely on proprietary LLM agents, which introduce unpredictability and limit accessibility, raising concerns about data privacy and model customization. This paper investigates whether open-source ...

Code Graph Model (CGM)
Code Graph Model ( CGM ): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks: Paper and Code . Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current solutions predominantly rely on proprietary LLM agents, which introduce unpredictability ...
We present Code Graph Models ( CGMs ), which innovatively integrate both semantic and structural information from code repositories into LLMs, enabling effective repository-level coding tasks without relying on agents or closed-source models .

Code Graph Model (CGM)
This paper introduces Code Graph Models ( CGMs ), which integrate repository code graph structures into the LLM's attention mechanism and map node attributes to the LLM's input space using a specialized adapter, and demonstrates this is possible by enabling LLMs to comprehend functions and files within codebases through their semantic information and structural dependencies. Recent advances in ...





This paper introduces Code Graph Models ( CGMs ), which integrate repository code graph structures into the LLM's attention mechanism and map node attributes to the LLM's input space using a specialized adapter, and demonstrates this is possible by enabling LLMs to comprehend functions and files within codebases through their semantic information ...