AI Travel Planner & Agentic Travel Concierge Platform

Apale, Ms. Srushti; Nagariya, Mr. Krish; Garole, Mr. Pankaj; Deshmukh, Ms. Dipshika

doi:https://doi.org/10.55041/ijcope.v2i10.103

Published on: October 2026

AI TRAVEL PLANNER & AGENTIC TRAVEL CONCIERGE PLATFORM

Ms. Srushti Apale Mr. Krish Nagariya Mr. Pankaj Garole Ms. Dipshika Deshmukh

Dr. N. S. Band

Information Technology Engineering, Prof. Ram Meghe Institute of Technology and Research, Badnera-Amravati, Maharashtra, India

DOI:https://doi.org/10.55041/ijcope.v2i10.103

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

Planning a trip today usually means jumping between many apps and browser tabs to research destinations, compare hotels, track budgets, sequence routes, and check the weather. Travellers often spend hours building a day-wise plan, only to throw parts of it away when the budget changes, the weather turns bad, or a popular attraction turns out to be crowded.

To address this, we present the AI Travel Planner and Agentic Travel Concierge Platform, a system that uses a Large Language Model (LLM) and an agentic AI architecture to create personalized, budget-aware travel itineraries. The user enters a destination, budget, trip duration, and interests, and a Preference Agent converts this into a traveller profile. Six specialised agents (Preference, Budget Optimization, Route Planning, Weather Intelligence, Crowd Prediction, and Replanning) then work together through an orchestration layer built with LangChain and Gemini models. They fetch live data from external APIs for maps, weather, and hotels, and use it to produce a day-wise schedule, hotel suggestions, route details, and a cost breakdown. The platform is built with a React.js frontend, a Python FastAPI backend, and a PostgreSQL data layer. Its key feature is conversational replanning: when conditions change, the Replanning Agent takes the current plan and the reason for change, then updates only the affected activities in structured JSON instead of regenerating the whole itinerary. This keeps the rest of the plan intact and saves time. The approach reduces manual planning effort and gives itineraries that match user preferences and constraints more closely than static, list-based planners.

Keywords— Agentic AI, conversational replanning, FastAPI, large language models, LangChain, multi-agent systems, personalized itinerary, React.js, travel planning.

How to Cite this Paper

Apale, S., Nagariya, K., Garole, P. & Deshmukh, D. (2026). AI Travel Planner & Agentic Travel Concierge Platform. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(10), 1-9. https://doi.org/10.55041/ijcope.v2i10.103

Apale, Srushti, et al.. "AI Travel Planner & Agentic Travel Concierge Platform." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 10, 2026, pp. 1-9. doi:https://doi.org/10.55041/ijcope.v2i10.103.

Apale, Srushti,Krish Nagariya,Pankaj Garole, and Dipshika Deshmukh. "AI Travel Planner & Agentic Travel Concierge Platform." International Journal of Creative and Open Research in Engineering and Management 02, no. 10 (2026): 1-9. https://doi.org/https://doi.org/10.55041/ijcope.v2i10.103.

Search & Index

References

Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis,Yih, T. Rocktäschel, S. Riedel, and D. Kiela, "Retrieval-augmented generation for knowledge-intensive NLP tasks," in Advances in Neural Information Processing Systems (NeurIPS), 2020, vol. 33, pp. 9459–9474.

Yao, J. Zhao, D. Yu, N. Du, I. Shafran,Narasimhan, and Y. Cao, "ReAct: Synergizing reasoning and acting in language models," in Proc. 11th Int. Conf. Learning Representations (ICLR), 2023.

OpenAI, "GPT-4 technical report," arXiv preprint arXiv:2303.08774, 2023.

Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, and D. Zhou, "Chain-of-thought prompting elicits reasoning in large language models," in Advances in Neural Information Processing Systems (NeurIPS), 2022, vol. 35, pp. 24824–24837.

Hong, X. Zheng, J. Chen, Y. Cheng, J.Wang, C. Zhang, Z. Wang, S. K. S. Yau, Z. Lin, L. Zhou, C. Ran, L. Xiao, and C. Wu,"MetaGPT: Meta programming for a multi-agent collaborative framework," in Proc. 12th Int. Conf. Learning Representations (ICLR), 2024.

-T. Tran, D. Dao, M.-D. Nguyen, Q.-V.Pham, B. O'Sullivan, and H. D. Nguyen, "Multi-agent collaboration mechanisms: A survey of LLMs," arXiv preprint arXiv:2501.06322, 2025.

de la Rosa, S. Gopalakrishnan, A. Pozanco, Z. Zeng, and D. Borrajo, "TRIP-PAL: Travel planning with guarantees by combining large language models and automated planners," arXiv preprint arXiv:2406.10196, 2024.

Chen, X. Ge, Z. Fu, Y. Xiao, and J. Chen, "TravelAgent: An AI assistant for personalized travel planning," arXiv preprint arXiv:2409.08069, 2024.

Chen, S. Wu, J. Zhou, and A. K. H. Tung, "Automatic itinerary planning for traveling services," IEEE Trans. Knowledge Data Eng., vol. 26, no. 3, pp. 514–527, 2014.

"Research on travel route planning optimization based on large language model," in IEEE Conf., IEEE Xplore, 2024. [Online]. Available:https://ieeexplore.ieee.org/document/1070448 9

Ethical Compliance & Review Process

•All submissions are screened under plagiarism detection.
•Review follows editorial policy.
•Authors retain copyright.
•Peer Review Type: Double-Blind Peer Review
•Published on: Oct 19 2026

CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License

Back to Volume 02, Issue 10 View All Issues Next Article

← Previous Article

AI Skin Disease Detection System

Next Article →

AI-Based Hiring Vs Traditional Hiring