Skip to content
 

LLMs and CodeAgents by Graham Neubig CMU

notes from lecture today:

Graham’s Lab LINK

LiveCodeBench a comparison framework + leaderboard from UC Berkeley

GorillaCS ability to accurately call a service API, leaderboard from UC Berkeley

SWE-Agent paper

AIDER Repo Understanding using Tree-sitter plus ChatGPT4 services
docs ovr site

Tree-sitter plugins

Code-Act execute code actions HF * repo

DeepSeek-Coder * DeepSeek-Coder v2 * DeepSeek LLM

CodeR — Muti-Agent plus Task Graphs

OpenCode Interpreter paper site

bonus content:

https://simonwillison.net/tags/ai-assisted-programming/

Team-ACE: a finetuned model of LLaMA-3.1-8B-Instruct (demo HF)with ZH_Code dataset