cs.AINov 17, 2026

Learning to Edit IFC Building Models: Verifiable Checkers as the Training Signal for Dependency-Aware Editing Agents

Authors: Jiaxin Zhang, Yao Luo, Yuze Dan, Yunqin Li, Bowen Wang

Organizations: Architecture and Design College, Nanchang University, Nanchang, China · School of Architecture and Urban Planning, Chongqing University, Chongqing, China · Key Laboratory of New Technology for Construction of Cities in Mountain Area (Ministry of Education), Chongqing University, China · Department of Intelligent Media, SANKEN, The University of Osaka, Osaka, Japan

Abstract

Editing a building information model in the Industry Foundation Classes (IFC) schema requires propagating changes to dependent elements while preserving unrelated entities. Existing language-model agents for IFC editing use prompted models without learning from edit outcomes. Target-file comparisons do not specify which alternative edits are allowed or which unrelated entities must remain unchanged. We present IfcGym, a CodeAct environment in which a language model edits IFC through executable code and four checkers verify validity relative to the input model, intent, dependency and preservation against a task specification. Their conjunction is strict success. IfcEdit distils verified teacher episodes into a Qwen3.5-9B student through supervised fine-tuning (SFT), then applies Group Relative Policy Optimization (GRPO) with strict success as the reward. On IfcEditBench, 1,990 editing tasks on 13 held-out real projects, the final student reaches 86.78% strict success, from 79.15% after SFT. The paired confidence interval for the difference from its teacher includes zero; the same recipe on a 27B model reaches 91.76% and exceeds the teacher. On the public benchmarks BIM-Edit and BIBIMBAP the final student scores 55.19 and 54.50. On IfcEditBench, the students outperform all prompted models except the teacher under matched tool access; both evaluated frameworks also score lower. Rewarding all four checkers yields 4.83 points more strict success than rewarding intent and validity alone.

Figures & tables

Explore similar work

CardsList
  1. BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling

    Jun 18, 2026Bharathi Kannan Nithyanantham, Clemens Kujat, Tobias Sesterhenn +5LLM EvaluationBuilding Information Modeling

  2. IFC-MCQ: Automatically Generating Multiple-Choice Benchmarks for Evaluating LLM Agents on IFC Data Retrieval

    Oct 21, 2026Rabindra Lamsal, Sisi Zlatanova, Xuesong ShenSynthetic Benchmark GenerationAI Agent Benchmarks

  3. IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations

    May 13, 2026Rabindra Lamsal, Sisi Zlatanova, Haowen Xu +2Building Information ModelingLLM Agents