HARDE

HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control Code release for HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control. The repository contains two complementary entry-point families: domains/: the Meta-Harness baseline and the two...

HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control

Large language model LLM agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime defenses that prevent unsafe action in execution across diverse risks while preserving benign-task utility. Existing system-level defenses either...