StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

2026-08-25

AI Summary

StarHarness通过分层搜索进化环境特定的代理框架，解决模型与企业环境不匹配问题，提高基准性能20-35个百分点。

Abstract

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 improvements to interface repairs, environment conventions, and operational knowledge that compresses search, with fewer false-positive diagnoses and shorter trajectories in several settings. StarHarness therefore offers a practical way to reduce persistent model-environment mismatch in tool-rich enterprise tasks.

Problem

• environment-specific agent harnesses
• fixed model weights
• enterprise environments

Innovation

• Stratified Search
• Harness Evolution
• Model-Environment Mismatch
• Enterprise Environments