AI RESEARCH

Natural-Language Agent Harnesses

arXiv CS.AI

ArXi:2603.25723v1 Announce Type: cross Agent performance increasingly depends on \emph{harness engineering}, yet harness design is usually buried in controller code and runtime-specific conventions, making it hard to transfer, compare, and study as a scientific object. We ask whether the high-level control logic of an agent harness can instead be externalized as a portable executable artifact. We