MiRL trains terminal agents against recurring misbehaviours instead of whole-task RL alone
Name the recurring wrong shell moves first, then start RL at those prefixes so fewer rollouts buy the same Terminal-Bench climb.
Read the piecePublished Frontier reporting tagged “Qwen”.
7 articles · Full archive · Topics
5 recent pieces
Name the recurring wrong shell moves first, then start RL at those prefixes so fewer rollouts buy the same Terminal-Bench climb.
Read the piece2 stories
An account called ChaosGPT uploaded an Italian offensive agent toolchain to both repositories on 16 Sep. The Qwen pull request is deleted. The DeepSeek pull request was still open at 16:01 SGT on 28 Sep.
Artificial Analysis confirms Qwen3.8-Max rose from 40 to 45 on its Intelligence Index. Alibaba has released no evidence that 33 automated cycles produced the gain.
New releases, then the constraint.