Agent Safety Should Be a Runtime Contract
The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI. We argue this is structurally insufficient for autonomous agents that execute code, mutate files, send messages, and modify databases. Agent safety should be a runtime contract enforced by the harness, and the contract has two complementary faces. The preventive face blocks dangerous actions before they happen via sandboxes, permission gates, output filters, and traject
Record details
Published: 10 August 2026
Source: HuggingFace Daily Papers
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 13 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy
arXiv · 10 August 2026
Multi-Agent AI Safety as an Institutional Design Problem
arXiv · 10 August 2026
Toward a Theory of Value in AI Alignment
arXiv · 10 August 2026
REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
arXiv red teaming query · 11 August 2026
MELLON - Multimodal Enhanced LLM for Online Navigation
arXiv · 10 August 2026
AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
arXiv · 11 August 2026
How to cite this record
ethics.ai (10 August 2026), “Agent Safety Should Be a Runtime Contract,” evidence record 18751, https://ethics.ai/record/18751 (originally published by HuggingFace Daily Papers).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.