StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
[Sztuczna inteligencja] Autorzy: Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav i 4 więcej
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, harness evolution improves full-benchmark performance by 20-35 percentage points over the default harness after 4-12 accepted changes per environment. These gains persist on tasks excluded from evolution and transfer without re-evolution across GPT and Qwen model families. Trace analysis links the improv…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja