Harness Engineering for Language Agents: The Harness Layer as Control, Agency, and Runtime
Preprint
- 23 April 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Language agents that act through tools, files, browsers, APIs, and persistent sessions are shaped by more than the base model or a single prompt. Their reliability depends on a harness layer that determines which instructions remain authoritative, what actions are available, how state is carried forward, and how failures are handled over time. This paper argues that this layer warrants explicit treatment in NLP. We propose and operationalize a working decomposition of the harness layer as control, agency, and runtime (CAR); situate harness engineering in the arc from software engineering through prompt and context engineering; and audit 63 harness-relevant works, suggesting a meaningful visibility gap between academic papers and public engineering notes. We further argue that many reported agent gains may be partly harness-sensitive rather than purely model-driven, and propose HarnessCard as a lightweight reporting artifact. Grounded in papers, benchmarks, protocols, and engineering notes collected through April 21, 2026, we argue that progress in language agents should report not only the model, but also the harness layer that turns capability into governed action.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Agent Harness for Large Language Model Agents: A SurveyPreprints.org, 2026
- The AutoResearch Moment: From Experimenter to Research DirectorPreprints.org, 2026
- AgentAI: A comprehensive survey on autonomous agents in distributed AI for industry 4.0Expert Systems with Applications, 2025
- Large Language Model Agent: A Survey on Methodology, Applications and ChallengesarXiv, 2025
- Survey on Evaluation of LLM-based AgentsarXiv, 2025
- Training Software Engineering Agents and Verifiers with SWE-GymarXiv, 2024
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- AgentBench: Evaluating LLMs as AgentsarXiv, 2023
- Voyager: An Open-Ended Embodied Agent with Large Language ModelsarXiv, 2023
- DSPy: Compiling Declarative Language Model Calls into Self-Improving PipelinesarXiv, 2023