Verifier feedback takes a 7B model from 14.0% to 62.9% pass@1 on Terraform.

Mohamed Jouini evaluates seven agentic strategies on IaC-Eval v2, 186 AWS/Terraform tasks with Rego v1 intent policies (arXiv 2607.20478). ReAct with MCP or ChromaDB-backed RAG lifts Qwen2.5-Coder 7B from 14.0% to 45.7%; iterative refinement on verifier feedback reaches 62.9% for the 7B and 84.4% for GPT-4o. GEPA reflective instruction optimization adds +7.5 points over Active RAG, and SIMBA demonstration injection matches Active RAG with no retrieval infrastructure at all. The diagnostic: 79% of post-refinement OPA policy failures are information-gap failures that vanish once the policy text is actually visible to the agent. Show the agent the rule it's being graded against.