The Last Harness You’ll Ever Build

arXiv:2604.21003v1 Announce Type: new
Abstract: AI agents are increasingly deployed on complex, domain-specific workflows — navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and synthesis, automating code review across unfamiliar repositories, and handling customer escalations that demand nuanced domain knowledge. textbfEach new task domain requires painstaking, expert-driven harness engineering: designing the prompts, tools, orchestration logic, and evaluation criteria that make a foundation model effective. We present a two-level framework that automates this process. At the first level, the textbfHarness Evolution Loop optimizes a worker agent’s harness $mathcalH$ for a single task: a Worker Agent $W_mathcalH$ executes the task, an Evaluator Agent $V$ adversarially diagnoses failures and scores performance, and an Evolution Agent $E$ modifies the harness based on the full history of prior attempts. At the second level, the textbfMeta-Evolution Loop optimizes the evolution protocol $Lambda = (W_mathcalH, mathcalH^(0), V, E)$ itself across diverse tasks, textbflearning a protocol $Lambda^(textbest)$ that enables rapid harness convergence on any new task — so that adapting an agent to a novel domain requires no human harness engineering at all. We formalize the correspondence to meta-learning and present both algorithms. The framework textbfshifts manual harness engineering into automated harness engineering, and takes one step further — textbfautomating the design of the automation itself.