v1.1.0: 10s of thousands of training trajectories
v1.1.0: 10s of thousands of training trajectories We're very excited to announce our new project SWE...
持续追踪核心框架、最新模型与重要系统升级轨迹。
v1.1.0: 10s of thousands of training trajectories We're very excited to announce our new project SWE...
SWE-agent 1.0.1 News: After our announcements for SOTA on SWE-Bench Lite and Verified, we now can cl...
SWE-agent 1.0 News So much new stuff! Here's a quick rundown of the cool new things you can do: ✨ Fa...
SWE-agent is SOTA on offensive cybersecurity SWE-agent EnIGMA (Enhanced Interactive Generative Model...
This is (mostly) a patch release, in particular fixing several issues that had been introduced by th...
What's Changed We sped up SWE-agent by 2x (timed with GPT4o). This is mostly due to faster communica...
What's Changed ✨ The big news is our brand new documentation ✨ Secondly, @ollmer added a new flag --...
What's Changed We’re excited to launch the SWE-agent web UI! Specify a bug, press start and watch SW...
What's Changed ✨ Features Run SWE-agent in the cloud using GitHub Codespaces Add GPT4-turbo model by...
What's Changed Added Allow to run on local repos (new flag: --repo_path ) by @klieret in #193 Patch ...