← 返回论文库

Devin: Autonomous AI Software Engineer

Cognition Labs · 2024
L2 · Production Agent SystemsProduct#coding-agent#production
CORE IDEA
第一个 production AI software engineer：给 GitHub issue，agent 自主 clone/写代码/跑测试/开 PR。
CONCRETE EXAMPLE
SWE-bench 13.86% solved（2024 launch，远超当时 SOTA 1.96%）。
L-ANCHOR · 为什么在这一层重要
production coding agent 起点

相关论文

FunSearch: Mathematical Discoveries from Program Search with LLMs
L12023
AI Scientist v1: Towards Fully Automated Open-Ended Scientific Discovery
L12024
AI Scientist v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
L12025
ASI-ARCH: AlphaGo Moment for Model Architecture Discovery
L12025