Story
arxiv_cs_ai · Oct 23, 2026 · paper
arxiv.orgOct 23, 2026
original source linked
In brief
Agent harnesses repeatedly invoke reasoning after tool feedback, even when an earlier call has already fixed the next action. We introduce HarnessMM (Harness Minus Minus), a method for improving harness token efficien...
Feed lens
agentharnessevalcodex