7 papers
IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval
Changyu Du, Alexander Vosseler, Filippo Mazza +1
Long-term memory is becoming a core capability of LLM-based agents, but existing evaluations largely test conversational recall in open-domain or persona-grounded settings. We argu…
BIM Information Extraction Through LLM-based Adaptive Exploration
Sylvain Hellin, Suhyung Jang, Stefan Fuchs +2
BIM models provide structured representations of building geometry, semantics, and topology, yet extracting specific information from them remains remarkably difficult. Current app…
A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction
Tobias Heimig-Elschner, Changyu Du, Anna Scheuvens +2
Agentic workflows driven by large language models (LLMs) are increasingly applied to Building Information Modelling (BIM), enabling natural-language retrieval, modification and gen…
From 'What-is' to 'What-if' in Human-Factor Analysis: A Post-Occupancy Evaluation Case
Xia Chen, Ruiji Sun, Philipp Geyer +2
Human-factor analysis typically employs correlation analysis and significance testing to identify relationships between variables. However, these descriptive ('what-is') methods, w…
Predictive Modeling: BIM Command Recommendation Based on Large-scale Usage Logs
Changyu Du, Zihan Deng, Stavros Nousias +1
The adoption of Building Information Modeling (BIM) and model-based design within the Architecture, Engineering, and Construction (AEC) industry has been hindered by the perception…
Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework
Changyu Du, Sebastian Esser, Stavros Nousias +1
The conventional BIM authoring process typically requires designers to master complex and tedious modeling commands in order to materialize their design intentions within BIM autho…