Elamur Research⌕
☰
home / papers / 2026 / PropGenie: A Multi-Agent Conversational Framework for Real Estate Assistance

PropGenie: A Multi-Agent Conversational Framework for Real Estate Assistance

Paper · 2026 · Chang Shen, Shaozu Yuan, Kuizong Wu et al.

Summary

PropGenie is an LLM-driven assistant for the Australian property market. It is built to handle the wide range of buyer questions, such as listings, mortgages, taxes and regulations, where wrong answers can be costly. The authors argue that a single agent fits this poorly. It lacks specialised skills, cannot cross-check its outputs against hallucinations, and needs bloated prompts to keep track of context. Instead, PropGenie splits the work among eight cooperating agents. A central RouteAgent decomposes requests, merges and reconciles outputs, rewrites multi-turn dialogue into standalone queries and tracks user emotion. The other agents handle listing search, loan recommendation, code-based tax and repayment calculation, and retrieval over structured, unstructured and multimodal knowledge gathered from official and financial sources. With GPT-4o as the backbone, the system was compared with OpenAI's o3-mini-high and Realty AI's Madison on real user queries. Expert raters preferred PropGenie most clearly for search, calculation and task execution, while the general model stayed competitive on policy QA and chitchat. The work shows that domain grounding and modular agents can make conversational assistants more dependable in high-stakes domains.

Key points

  • The architecture has eight agents: RouteAgent, SearchAgent, RecAgent, CalcAgent, RagAgent, MMAgent, TaskAgent and ChatAgent. Together they cover ten tasks, including stamp duty and land tax calculation, interest-rate QA and property project QA.
  • SearchAgent pulls listings through the Domain API and uses an LLM to re-rank the top 50 results down to 3. CalcAgent turns government tax rules into formulas and runs Python code to compute answers.
  • RagAgent converts crawled policy pages into LLM-filtered QA pairs stored in a vector database. Interest rates come from a structured database refreshed from bank APIs.
  • For human evaluation, 500 queries were sampled from a 6,398-query test set. Five real estate experts ranked the responses blind, with inter-annotator agreement of 0.82.
  • PropGenie won more than 55% of comparisons against o3-mini-high on search and recommendation, calculation and task execution. Against Madison, it won more than 65% in every category except chitchat ("Other").

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 624 works

Cite

Cite as Chang Shen, Shaozu Yuan, Kuizong Wu, Long Xu and Meng Chen. 2026. PropGenie: A Multi-Agent Conversational Framework for Real Estate Assistance. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.eacl-demo.3

@inproceedings{shen2026propgenie,
  title = {{PropGenie: A Multi-Agent Conversational Framework for Real Estate Assistance}},
  author = {Chang Shen, Shaozu Yuan, Kuizong Wu, Long Xu and Meng Chen},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-demo.3},
  url = {https://doi.org/10.18653/v1/2026.eacl-demo.3}
}

References

40 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dawei Gao, Zitao Li, Xuchen Pan, Weirui Kuang, Zhijian Ma, Bingchen Qian, Fei Wei, Wenhao Zhang, Yuexiang Xie, Daoyuan Chen, Liuyi Yao, Hongyi Peng, Zeyu Zhang, Lin Zhu, Chen Cheng, Hongzhu Shi, Yaliang Li, Bolin Ding, and Jingren Zhou. 2024a. Agentscope: A flexible yet robust multi-agent platform.… — [arXiv:2402.14034](https://arxiv.org/abs/2402.14034) find
  2. Guanqun Bi, Lei Shen, Yanan Cao, Meng Chen, Yuqiang Xie, Zheng Lin, and Xiaodong He. 2023. DiffusEmp: A diffusion model-based framework with multi-grained control for empathetic response generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1:… find
  3. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024b. Retrieval-augmented generation for large language models: A survey. Preprint, arXiv:2312.10997.
  4. Tuan-Dung Cao and Quang H. Nguyen. 2021. An Approach for Building Effective Real Estate Chatbots in Vietnamese, pages 221–229. Springer International Publishing, Cham. find
  5. GeminiTeam, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, and et al. 2024. Gemini: A family of highly capable multimodal models. Preprint, arXiv:2312.11805.
  6. Daixuan Cheng, Yuxian Gu, Shaohan Huang, Junyu Bi, Minlie Huang, and Furu Wei. 2024. Instruction pre-training: Language models are supervised multitask learners. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 2529–2550, Miami, Florida, USA. Associati…
  7. Benedikt Gloria, Johannes Melsbach, Sven Bienert, and Detlef Schoder and. 2025. Real-gpt: Efficiently tailoring llms for informed decision-making in the real estate industry. Journal of Real Estate Portfolio Management, 31(1):56–72. find
  8. Jiaxi Cui, Munan Ning, Zongjian Li, Bohua Chen, Yang Yan, Hao Li, Bin Ling, Yonghong Tian, and Li Yuan. 2024. Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model. Preprint, arXiv:2306.16092.
  9. Kasper Raupach Haurum, Ruiqi Ma, and Wen Long. 2024. Real estate with ai: An agent based on langchain. Procedia Computer Science, 242:1082– 1088. 11th International Conference on Information Technology and Quantitative Management (ITQM 2024). find
  10. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, and et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. Preprint, arXiv:2501.12948.
  11. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. MetaGPT: Meta programming for a multi-agent collaborative framework. In The T…
  12. Xiaofei Dong, Xueqiang Zhang, Weixin Bu, Dan Zhang, and Feng Cao. 2024. A survey of llm-based agents: Theories, technologies, applications and suggestions. In 2024 3rd International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC), pages 407–413. IEEE. find
  13. Susan Hudson-Wilson, Jacques Gordon, Frank Fabozzi, Mark Anson, and S. Giliberto. 2005. Why real estate? The Journal of Portfolio Management, 31:12– 21. find
  14. Zane Durante, Qiuyuan Huang, Naoki Wake, Ran Gong, Jae Sung Park, Bidipta Sarkar, Rohan Taori, Yusuke Noda, Demetri Terzopoulos, Yejin Choi, Katsushi Ikeuchi, Hoi Vo, Li Fei-Fei, and Jianfeng Gao. 2024. Agent ai: Surveying the horizons of multimodal interaction. Preprint, arXiv:2401.03568. — [arXiv:2401.03568](https://arxiv.org/abs/2401.03568) find
  15. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Proc…
  16. J. Elster. 2016. Sour Grapes. Cambridge Philosophy Classics. Cambridge University Press. find
  17. Jiabao Fang, Shen Gao, Pengjie Ren, Xiuying Chen, Suzan Verberne, and Zhaochun Ren. 2024. A multi-agent conversational recommender system. arXiv preprint arXiv:2402.01135. — [arXiv:2402.01135](https://arxiv.org/abs/2402.01135) find
  18. Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024a. Llms-as-judges: A comprehensive survey on llm-based evaluation methods. Preprint, arXiv:2412.05579.
  19. Sorouralsadat Fatemi and Yuheng Hu. 2024. Enhancing financial question answering with a multi-agent reflection framework. In Proceedings of the 5th ACM International Conference on AI in Finance, pages 530–537. find
  20. Junyou Li, Qin Zhang, Yangbin Yu, QIANG FU, and Deheng Ye. 2024b. More agents is all you need. Transactions on Machine Learning Research. find
  21. OpenAI. 2025. Openai o3-mini system card. find
  22. Fahim Ullah, Samad M. E. Sepasgozar, and Changxin Wang. 2018. A systematic review of smart real estate technology: Drivers of, and barriers to, the use of digital disruptive technologies and online platforms. Sustainability, 10(9). find
  23. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and et al. 2024a. Gpt-4 technical report. Preprint, arXiv:2303.08774.
  24. Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, and Zhoujun Li. 2025a. MAC-SQL: A multi-agent collaborative framework for text-to-SQL. In Proceedings of the 31st International Conference on Computational Linguistics, pages 540–…
  25. OpenAI, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, and et al. 2024b. Gpt-4o system card. Preprin…
  26. Junlin Wang, Jue WANG, Ben Athiwaratkun, Ce Zhang, and James Zou. 2025b. Mixture-of-agents enhances large language model capabilities. In The Thirteenth International Conference on Learning Representations. find
  27. Surbhi Pagar. 2024. Lawbot : From documents to answers, unveiling a new era in real estate legal assistance. Interantional Journal of Scientific Research In Engineering And Management, 08:1–5. find
  28. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation. Preprint, arXiv:2308.08155.
  29. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, dahai li, Zhiyuan Liu, and Maosong Sun. 2024. ToolLLM: Facilitating large language models to master 16000+ real…
  30. John Yang, Carlos Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024a. Swe-agent: Agent-computer interfaces enable automated software engineering. Advances in Neural Information Processing Systems, 37:50528– 50652.
  31. Tho Quan, Trung Trinh, Dang Ngo, Hon Pham, Long Hoang, Hung Hoang, Thanh Thai, Phong Vo, Dang Pham, and Trung Mai. 2018. Lead engagement by automated real estate chatbot. In 2018 5th NAFOSTED Conference on Information and Computer Science (NICS), pages 357–359. find
  32. Shuling Yang, Hanzhu Chen, and Binbin Fang. 2024b. Qudial: A quadruple-driven dialogue system for real estate consulting services. In Proceedings of the 2024 16th International Conference on Machine Learning and Computing, ICMLC ’24, page 609–615, New York, NY, USA. Association for Computing Machine… find
  33. Philip Seagraves. 2023. Real Estate Insights: Is the AI revolution a real estate boon or bane? Journal of Property Investment & Finance, 42(2):190–199. find
  34. Xiangru Tang, Anni Zou, Zhuosheng Zhang, Ziming Li, Yilun Zhao, Xingyao Zhang, Arman Cohan, and Mark Gerstein. 2023. Medagents: Large language models as collaborators for zero-shot medical reasoning. arXiv preprint arXiv:2311.10537.
  35. Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, and Sercan O Arik. 2024. Chain of agents: Large language models collaborating on long-context tasks. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  36. A. Tanović and A. Ćerimagić Hasibović. 2024. Automated real estate chatbot. In 2024 47th MIPRO ICT and Electronics Convention (MIPRO), pages 241– 246. find
  37. Jun Zhao, Can Zu, Hao Xu, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. Longagent: Scaling language models to 128k context through multi-agent collaboration. Preprint, arXiv:2402.11550. — [arXiv:2402.11550](https://arxiv.org/abs/2402.11550) find
  38. SIMA Team, Maria Abi Raad, Arun Ahuja, Catarina Barros, Frederic Besse, Andrew Bolt, Adrian Bolton, Bethanie Brownfield, Gavin Buttimore, Max Cant, Sarah Chakera, Stephanie C. Y. Chan, Jeff Clune, and et al. 2024. Scaling instructable agents across many simulated worlds. Preprint, arXiv:2404.10179. — [arXiv:2404.10179](https://arxiv.org/abs/2404.10179) find
  39. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Preprint, arXiv:2306.05685.
  40. Param Thakkar and Anushka Yadav. 2024. Personalized recommendation systems using multimodal, autonomous, multi agent systems. Preprint, arXiv:2410.19855. — [arXiv:2410.19855](https://arxiv.org/abs/2410.19855) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/shen-2026-propgenie-multi-agent-conversational-framework/