Natural-Language Agent Harnesses

Linyue Pan, Zou Lexiao, Shuo Guo, Jingchen Ni, Hai-Tao Zheng

Natural-Language Agent Harnesses: 20 upvotes on Hugging Face Daily Papers, #8 of 15 papers on 2026-03-30. Day-by-day upvote history. It lost 7 votes when the Hub removed votes in bulk.

Agent performance increasingly depends on 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 introduce Natural-Language Agent Harnesses (NLAHs), which express harness behavior in editable natural language, and Intelligent Harness Runtime (IHR), a shared runtime that executes these harnesses through explicit contracts, durable artifacts, and lightweight adapters. Across coding and computer-use benchmarks, we conduct controlled evaluations of operational viability, module ablation, and code-to-text harness migration.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.