YerbaPage/Awesome-Repo-Level-Code-Generation

A living collection of frontier research on code agents, from the code we build to the worlds we act in.

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Cool links & research papers related to Machine Learning applied to source code (MLonCode)

[TOSEM'25] The official GitHub page for the survey paper "A Survey on Large Language Models for Code Generation".

CodeRAG-Bench: Can Retrieval Augment Code Generation?

Code associated with the paper An AI system to help scientists write expert-level empirical software

Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Solutions to conduct Agentic RAG from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.