John Yang
CS PhD student at Stanford; co-creator of SWE-Bench, SWE-Agent, and WebShop; started the SWE-Agent project at Princeton.
- Role
- grad-student
- Currently at
- Stanford University
- twitter.com/johnyangg
- GitHub
- github.com/john-b-yang
- Scholar
- scholar.google.com/citations
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
arXiv 2026
mini-SWE-agent: A Minimal Reference Agent for SWE-bench
blog
OpenThoughts: Data Recipes for Reasoning Models
arXiv 2025
SWE-smith: Scaling Data for Software Engineering Agents
arXiv 2025
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
ICLR
EnIGMA: Enhanced Interactive Generative Model Agent for CTF Challenges
arXiv 2024
Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study
arXiv 2024
InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
NeurIPS 2023 11
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
arXiv 2022
Eval contributions
2Affiliations
Previously
Frequent co-authors
10from 9 papers
Karthik Narasimhan
professor
Ofir Press
postdoc
Shunyu Yao
researcher
Ludwig Schmidt
professor
Alexander Wettig
researcher
Binyuan Hui
Carlos E. Jimenez
Etash Guha
researcher
Jeffrey Li
Jenia Jitsev