Pinned Loading
Repositories
Showing 10 of 80 repositories
- SWE-agent Public
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.
princeton-nlp/SWE-agent’s past year of commit activity - il-scaling-in-games Public
Official code repo of "Scaling Laws for Imitation Learning in Single-Agent Games"
princeton-nlp/il-scaling-in-games’s past year of commit activity