Natural-Language Agent Harnesses
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. A...
| Authors | Linyue Pan, Lexiao Zou, Shuo Guo et al. |
|---|---|
| Primary category | cs.CL |
| Published | 26 March 2026 |
| Last updated at source | 18 May 2026 |
Connected in the knowledge graph
- zhongweixie/A-Survey-on-AI-Agent-HarnessDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.