I'm John! Currently a Princeton University graduate student.
Check out john-b-yang.github.io for more.
I'm John! Currently a Princeton University graduate student.
Check out john-b-yang.github.io for more.
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?
[NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898
Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.