LoopArena: evaluating runtime control for coding agents #235
burgerseater
started this conversation in
Show and tell
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Hi AgentBench community,
I’d like to share a benchmark from an adjacent agent-evaluation setting. LoopArena evaluates how well a model can guide a separate, fixed coding agent through long-running software-development tasks.
GitHub: https://github.com/AMAP-ML/LoopArena
Paper: https://huggingface.co/papers/2608.28281
ModelScope: https://www.modelscope.cn/papers/2608.28281
We hope it may be useful to researchers studying agent control and evaluation. Feedback is welcome.
Disclosure: I’m one of the authors.
All reactions