2026-10-05T21:32:54Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:28036 2026-10-05T06:44:05Z ddc:004 open_access

TerraRepair: A Tool-Grounded LLM Agent for Infrastructure-As-Code Repair Mengistu, Minase Mekete Di Rocco, Juri Nguyen, Phuong T. Di Ruscio, Davide Infrastructure as Code automated repair large language models cloud security Background. Infrastructure-as-Code (IaC) scanners detect cloud misconfigurations in Terraform and other IaC languages before deployment, but repairing the flagged configurations remains largely manual. Recent Large Language Model (LLM)-based repair approaches can repair some findings, but may hallucinate unsupported constructs or suppress warnings without fixing the issue. Aims. We study whether tool grounding can improve LLM-based Terraform repair, and when a finding should be escalated because the required deployment-specific context is not available. Method. We present TerraRepair, a prototype of a tool-grounded LLM agent for Terraform repair with structured escalation. TerraRepair retrieves dependency context from Terraform references, consults the installed provider schema, and re-runs the scanner before returning a candidate repair. When the required context is absent, TerraRepair escalates instead of fabricating a plausible fix. Results. We evaluate our tool on two vulnerable-by-design Terraform repositories using two IaC security scanners, Checkov and Trivy, across AWS, Azure, and GCP. On the combined AWS benchmark, TerraRepair improves scanner-verified fix rates from 26.6% to 78.4% on Checkov and from 44.8% to 72.4% on Trivy, compared with a controlled one-shot baseline. It also reduces the baseline’s 44.8-73.6 percentage point (pp) claimed-vs-verified repair gap to under 5 pp. In a sampled semantic audit covering AWS only, 78.9% of TerraRepair’s scanner-verified AWS repairs are labeled as correct under a majority-vote protocol with two LLM judges and one author. Conclusions. These emerging results show that tool grounding can substantially improve scanner-verified LLM-based IaC repair on the studied benchmarks, while missing deployment-specific context remains the main knowledge boundary for full autonomy. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Minase Mekete Mengistu and Juri Di Rocco and Phuong T. Nguyen and Davide Di Ruscio 2026 Is Part Of LIPIcs, Volume 394, 20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ESEM.2026.68 urn:nbn:de:0030-drops-280363 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.68 eng https://creativecommons.org/licenses/by/4.0/legalcode