#artificial intelligence
Sep 2026
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Mid-Harness is introduced, which samples and verifies candidate actions before forwarding one for execution, while keeping the generator and harness unchanged, and identifies action scaling as a promising target for test-time compute scaling in terminal agents.
Minki Kang, Ryo Hachiuma, Shao-Kun Zhang et al.
· arXiv.org · 3 citations