SOURCE-LINKED INTELLIGENCE

StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include prompt and task framing, tool interfaces, skills, MCP-backed providers, subagent structure, and agent-loop configuration. StarHarness constructs a compact evolution pool by stratifying tasks according to baseline failure behavior, separates proposer-visible search tasks from proposer-hidden selection tasks, and reserves held-out tasks for evaluating generalization. Across ITBench SRE, EnterpriseOps-Gym ITSM, and AutomationBench Finance, harnes

Read original source ↗ Open in workspace

recordType

paper

region

Global