No AI summary available for this article.
Why It Matters
We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.24804v1 · Indexed 5 days ago