Travel Genie: A Multi-Agent Collaborative Architecture for Autonomous Itinerary Synthesis and Real-Time Disruption Recovery

Authors

Sakthivell Kannan

Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia (Malaysia)

Siti Azirah Asmai

Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia (Malaysia)

Suhail S.M.Alqrinawi

Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia (Malaysia)

Nur Diana Izzani Masdzarif

Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia (Malaysia)

Muhammad Hafidz Fazli Md Fauadi

Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia (Malaysia)

Article Information

DOI: 10.47772/IJRISS.2026.100900705

Subject Category: Multi-agent Systems

Volume/Issue: 10/9 | Page No: 10204-10211

Publication Timeline

Submitted: 2026-09-26

Accepted: 2026-10-01

Published: 2026-10-21

Abstract

Conventional trip-planning tools and pre-packaged online travel agency (OTA) bundles are ill-suited to a travel environment that changes in real time: they lock in a fixed budget, a fixed route, and a fixed set of assumptions about weather and transport, so a single delayed flight or a rained-out afternoon can invalidate an entire schedule. Feeding the same problem to a general-purpose large language model does not solve it either, since a single monolithic prompt tends to invent attractions that do not exist, misjudge travel times between stops, and ignore hard budget ceilings. This paper introduces TravelGenie, a production-oriented mobile platform that instead splits the planning task across seven cooperating, purpose-built AI agents responsible for destination research, itinerary drafting, logistics and lodging, budget enforcement, time-block scheduling, fatigue management, and live disruption recovery. The system is delivered through a three-tier stack a React Native / Expo SDK 57 mobile client, a FastAPI backend, and an SQLite store acting as the single source of truth with the agent pipeline built on the Agno orchestration framework and served by Groq-hosted LLM inference, supplemented by SerpAPI flight data and OpenWeatherMap forecasts. Itineraries can be exported as RFC 5545-compliant .ics files for direct import into Apple Calendar, Google Calendar, or Outlook. Controlled testing shows the pipeline resolving 98.2% of injected disruption scenarios (heavy rain, flight delay, and sudden venue closure) and holding 94.8% budget-compliance accuracy, while completing end-to-end agent execution in under 1.25 seconds and sustaining 60 fps on the mobile client a clear improvement over single-prompt baselines built on GPT-4o, Claude 3.5 Sonnet, and Llama-3-70B.

Keywords

multi-agent systems; travel itinerary planning; large language models; dynamic rescheduling; calendar export; mobile computing; AI in tourism

Downloads

References

1. Agno AI Framework Team. (2024). Agno: Building multi-agent systems with memory, knowledge and tools [Technical documentation]. https://docs.agno.com [Google Scholar] [Crossref]

2. Buhalis, D., & Law, R. (2008). Progress in information technology and tourism management: 20 years on and 10 years after the Internet—The state of eTourism research. Tourism Management, 29(4), 609–623. https://doi.org/10.1016/j.tourman.2008.01.005 [Google Scholar] [Crossref]

3. Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., Ye, W., Zhang, Y., Chang, Y., Yu, P. S., Yang, Q., & Xie, X. (2024). A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology, 15(3), Article 39, 1–45. https://doi.org/10.1145/3641289 [Google Scholar] [Crossref]

4. Desruisseaux, B. (Ed.). (2009). Internet calendaring and scheduling core object specification (iCalendar) (RFC 5545). Internet Engineering Task Force. https://doi.org/10.17487/RFC5545 [Google Scholar] [Crossref]

5. Expo Developer Network. (2024). Upgrading Expo SDK and React Native workflows [Documentation]. https://docs.expo.dev [Google Scholar] [Crossref]

6. Gretzel, U., Sigala, M., Xiang, Z., & Koo, C. (2015). Smart tourism: Foundations and developments. Electronic Markets, 25(3), 179–188. https://doi.org/10.1007/s12525-015-0196-8 [Google Scholar] [Crossref]

7. Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S. K. S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., & Schmidhuber, J. (2024). MetaGPT: Meta programming for a multi-agent collaborative framework. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024). https://doi.org/10.48550/arXiv.2308.00352 [Google Scholar] [Crossref]

8. Liu, R., Piplani, R., & Toro, C. (2023). A deep multi-agent reinforcement learning approach to solve dynamic job shop scheduling problem. Computers & Operations Research, 159, Article 106294. https://doi.org/10.1016/j.cor.2023.106294 [Google Scholar] [Crossref]

9. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. https://doi.org/10.48550/arXiv.1707.06347 [Google Scholar] [Crossref]

10. Singh, S. S., Joshi, R., & Gupta, D. (2025). An advantage actor-critic approach for energy-conscious scheduling in flexible job shops. Journal on Artificial Intelligence, 7(1), 177–203. https://doi.org/10.32604/jai.2025.065078 [Google Scholar] [Crossref]

11. Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., & Wen, J.-R. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), Article 186345. https://doi.org/10.1007/s11704-024-40231-1 [Google Scholar] [Crossref]

12. Wooldridge, M. (2009). An introduction to multiagent systems (2nd ed.). John Wiley & Sons. [Google Scholar] [Crossref]

13. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., Awadallah, A. H., White, R. W., Burger, D., & Wang, C. (2024). AutoGen: Enabling next-gen LLM applications via multi-agent conversation. In Proceedings of the First Conference on Language Modeling (COLM 2024). https://doi.org/10.48550/arXiv.2308.08155 [Google Scholar] [Crossref]

14. Xie, J., Zhang, K., Chen, J., Zhu, T., Lou, R., Tian, Y., Xiao, Y., & Su, Y. (2024). TravelPlanner: A benchmark for real-world planning with language agents. In Proceedings of the 41st International Conference on Machine Learning (PMLR Vol. 235, pp. 54590–54613). https://proceedings.mlr.press/v235/xie24j.html [Google Scholar] [Crossref]

Metrics

Views & Downloads

Similar Articles