# Interactive Clarification for Cloud Infrastructure-as-Code Synthesis

arXiv: https://arxiv.org/abs/2604.02382 · HTML: https://mlsanity.com/paper/2604.02382/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Automatic Root Cause Analysis via Large Language Models for Cloud Incidents](https://mlsanity.com/paper/2305.15778/) (2023)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [Interactive Code Generation via Test-Driven User-Intent Formalization](https://mlsanity.com/paper/2208.05950/) (2022)
- [AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds](https://mlsanity.com/paper/2501.06706/) (2025)
- [Active Task Disambiguation with LLMs](https://mlsanity.com/paper/2502.04485/) (2025)
- [Building AI Agents for Autonomous Clouds: Challenges and Design Principles](https://mlsanity.com/paper/2407.12165/) (2024)
- [AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL](https://mlsanity.com/paper/2508.15276/) (2025)
- [A Survey of using Large Language Models for Generating Infrastructure as Code](https://mlsanity.com/paper/2404.00227/) (2024)
- [Cloud Infrastructure Management in the Age of AI Agents](https://mlsanity.com/paper/2506.12270/) (2025)
- [Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents](https://mlsanity.com/paper/2510.20211/) (2025)

## Abstract (arXiv)

The scale and complexity of modern cloud infrastructure have made "Infrastructure-as-Code" (IaC) essential for managing deployments through declarative configurations. While large language models (LLMs) are increasingly used to generate IaC configurations from natural language, user requests are often ambiguous and underspecified. Unlike traditional code generation, it is costly and time-consuming to test IaC configurations during the synthesis, forcing the LLMs into an almost one-shot regime. We observe that ambiguity in IaC synthesis exhibits a compositional structure: configurations decompose into three axes (resources, topology, attributes) where higher-level decisions constrain lower-level ones. We propose a training-free, multi-level disambiguation framework that generates diverse candidate specifications, identifies structural disagreements across these axes, ranks them by informativeness, and produces targeted clarification questions that progressively narrow the configuration space. We further introduce Ambig-IaC, an expert-verified benchmark of 300 validated IaC tasks with ambiguous requests, and define evaluation metrics based on graph edit distance and exact attribute matching. Comprehensive experiments show that our method outperforms existing interactive clarification baselines, with gains that scale with the interaction budget and generalize across models. Extensive ablation studies and analyses further demonstrate its robustness for interactive IaC synthesis.