Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64973
Volume:
10 |
6 |
Jun 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Computer Science and Engineering (Artificial Intelligence and Machine Learning)
CMR Technical Campus, Hyderabad

Computer Science and Engineering (Artificial Intelligence and Machine Learning)
CMR Technical Campus, Hyderabad

Computer Science and Engineering (Artificial Intelligence and Machine Learning)
CMR Technical Campus, Hyderabad

Computer Science and Engineering (Artificial Intelligence and Machine Learning)
CMR Technical Campus, Hyderabad
Modern travelers face a persistent dilemma in balancing cost efficiency with environmental responsibility. This paper proposes an AI-driven multi-agent platform that addresses this challenge by coordinating specialized agents to generate travel itineraries optimized simultaneously for cost-effectiveness, emission reduction, and user preference satisfaction. The architecture integrates generative language models to produce transparent, human-readable explanations for each recommendation. Experimental analysis demonstrates a 15% reduction in carbon emissions compared to price-only optimization approaches, while keeping costs within a 10% margin, confirming the feasibility of jointly optimizing financial and environmental objectives in real-world travel planning.
KEYWORDS
We introduced an agent-based system for automated, sustainable, and budget-friendly travel planning using multi-objective optimization. Specialized agents (Cost, Environmental, Personalization, and Coordination) provide a holistic approach to the challenges of modern travel planning. Evaluation demonstrates an average 15% reduction in emissions over price-only optimization while keeping cost increases within a 10% margin. User studies validate high preference satisfaction (8.2-8.9/10), explanation comprehensibility (8.1/10), and decision confidence (84%). Computational efficiency under 30 seconds confirms real-time applicability. The modular multi-agent architecture allows independent refinement of each component, and the integration of LLMs bridges the gap between optimization output and human understanding through natural-language explanations, demonstrating that economic and ecological objectives can be considered simultaneously.
[1] D. Camacho et al., “Intelligent Travel Planning: A Multi-Agent System,” Autonomous Agents and Multi-Agent Systems, vol. 4, no. 4, pp. 387–392, 2001. [2] U. A. Lenfers et al., “Multi-Modal Travel Planning in an Agent-Based Model,” Land, vol. 10, no. 11, p. 1179, 2021. [3] M. Lenzen et al., “The Carbon Footprint of Global Tourism,” Nature Climate Change, vol. 8, no. 6, pp. 522–528, 2018. [4] S. Gössling et al., “Tourism and Climate Change Mitigation: A Review,” Tourism Management, vol. 94, p. 104566, 2022. [5] S. Rodríguez-Moreno et al., “Sustainable Tourism Carbon Footprint Approach,” Journal of Cleaner Production, vol. 369, p. 133222, 2022. [6] H. Zhao et al., “Explainability for Large Language Models: A Survey,” ACM Trans. Intelligent Systems, vol. 15, no. 2, p. 20, 2024. [7] H. Luo and L. Specia, “Explainability for LLMs: A Survey,” arXiv:2401.12874, 2024. [8] J. Ruiz-Meza et al., “Multi-Objective Sustainable Trip Planning,” Expert Systems with Applications, vol. 237, p. 121479, 2024. [9] J. Ruiz-Meza and J. R. Montoya-Torres, “Tourist Trip Design with Environmental Considerations,” Annals of Operations Research, vol. 305, no. 1, pp. 227–249, 2021. [10] J. Ruiz-Meza et al., “Multi-Objective Fuzzy Tourist Trip Design,” Sustainability, vol. 13, no. 17, p. 9771, 2021.
Publication Date
6/14/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...