# A Building as a Repository: KIR, a Typed Intermediate Representation for Agent-Authored Building Information Models

arXiv: https://arxiv.org/abs/2609.14578 · HTML: https://mlsanity.com/paper/2609.14578/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 66 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design](https://mlsanity.com/paper/2007.08506/) (2020)
- [IPFS - Content Addressed, Versioned, P2P File System](https://mlsanity.com/paper/1407.3561/) (2014)
- [CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis](https://mlsanity.com/paper/1904.01920/) (2019)
- [Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path](https://mlsanity.com/paper/1908.06702/) (2019)
- [Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attention](https://mlsanity.com/paper/1908.11025/) (2019)
- [Large Language Models for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2505.08137/) (2025)
- [BIM-GPT: a Prompt-Based Virtual Assistant Framework for BIM Information Retrieval](https://mlsanity.com/paper/2304.09333/) (2023)
- [BIMgent: Towards Autonomous Building Modeling via Computer-use Agents](https://mlsanity.com/paper/2506.07217/) (2025)
- [Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework](https://mlsanity.com/paper/2408.08054/) (2024)
- [ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation](https://mlsanity.com/paper/2607.05750/) (2026)
- [CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation](https://mlsanity.com/paper/2608.00891/) (2026)
- [FloorPP-Net: Reconstructing Floor Plans using Point Pillars for Scan-to-BIM](https://mlsanity.com/paper/2106.10635/) (2021)
- [A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction](https://mlsanity.com/paper/2601.00809/) (2025)

## Abstract (arXiv)

Autonomous agents that author building information models need more than access to a host API. They need a representation of what they intended, what a compiler decided on their behalf, what was refused, what was observed after execution and what remains unknown. We present KIR, a typed intermediate representation in which a building is authored as a program held in a versioned repository and lowered to host applications as build targets. KIR is organised around seven ways in which a generator writing into a stateful, partially observable host goes silently wrong, and gives each a representation in data: ambiguous selectors become typed refusals with candidates; defaults keep their provenance; obligations that will not be checked are named before execution; vacuous witnesses are rejected statically; a lost transaction response becomes the state UNCONFIRMED with a verify-before-retry rule; the reverse path obeys a census invariant; and decisions are bound by digest to the state they were made against. On a pinned snapshot with 83 operation contracts and Revit as the only backend, offline experiments refuse 29 of 42 stress-test programs with diagnostic codes and no uncaught exception, name 38 of 377 witness obligations as unwitnessable, admit 31 of 100 combinations of execution, witness and acceptance states under seven stated invariants, and find no vacuous witness in 219 certificate runs; a 60-storey tower is 11,263 characters as KIR against 3,709,235 characters of emitted C#. Native Revit runs are reported from project records and kept separate from reproduced results. A controlled comparison with agents that write host code directly is specified but not yet executed; it is the principal open question.