Natural-Language Agent Harnesses

TL;DR

This paper introduces Natural-Language Agent Harnesses (NLAHs) and an Intelligent Harness Runtime (IHR) to represent and execute agent harness policies as editable natural-language documents, improving transparency and reusability.

Contribution

The paper presents a novel approach to modeling agent harnesses as natural-language objects with an interpretable runtime, enabling better inspection, transfer, and analysis.

Findings

NLAHs achieve comparable task outcomes to traditional code-based harnesses.

IHR-executed NLAHs have shorter static harness policies.

Explicit harness modules are shown to be analyzable.

Abstract

Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to inspect, compare, transfer, and ablate. This paper asks whether the reusable design pattern of an agent harness can be represented as an executable natural-language object. We introduce Natural-Language Agent Harnesses (NLAHs), editable documents that describe run-level harness policy, and Intelligent Harness Runtime (IHR), a shared runtime that interprets these documents into agent calls, handoffs, state updates, validation gates, and artifact contracts. Across coding, terminal-use, and computer-use benchmarks, IHR-executed NLAHs achieve comparable task outcomes to code and prompted realizations, while exposing much shorter static harness policies. Module ablations further show that explicit harness modules are analyzable. These results suggest that agent harnesses can be turned from incidental glue around models into scientific representation objects.