StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%Scaling agentic AI: Enterprise patterns without vendor lock-in →
- PossiblePossibly related (embedding) · 57%Pluggable by design: An agent mesh for software modernization that adopts the next model release →
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “StarHarness: Evolving Harnesses with Stratified Search for E” ≈ “strands-agents/harness-sdk””
- FuzzySimilar title/name (fuzzy) · 59%browser-use/browser-harness →
“Fuzzy title match (0.73): “StarHarness: Evolving Harnesses with Stratified Search for E” ≈ “browser-use/browser-harness””
- LinkedLinked via arxiv author · 85%Esakkivel Esakkiraja →
“StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments”
- LinkedLinked via arxiv author · 85%Denis Akhiyarov →
“StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments”
- LinkedLinked via arxiv author · 85%Vikas Yadav →
“StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments”
- LinkedLinked via arxiv author · 85%Sai Rajeswar →
“StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments”