← Publications
preprint2026

Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions

Xiaofei Yuan, Yan Zhang, Shaobo Qiao, Huangleshuai He, Leyan Ni, Mingchen Ju, Lujia Yang, Sijia Xu, Yifu Tang, Zhengyi Yang*

arXiv

RAIDS Lab Authors

Huangleshuai He
Huangleshuai He
Adjunct
Lujia Yang
Lujia Yang
MPhil
Zhengyi Yang
Zhengyi Yang
(corresponding author)
Director

Details

Year
2026
Venue
arXiv

Research Area

Responsible Data IntelligenceData for Real-World Applications

Tags

Travel PlanningPlan RepairAgentsLLM

Resources

arXiv ↗

Abstract

Travel-planning agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attraction closures. Revising these itineraries involves full replanning, classical plan repair, and LLM-based travel-agent revision, whose differing task formulations and evaluation protocols hinder comparison. We conduct a systematic empirical study using two TREK-derived benchmark sets: 500 single-disruption cases, including feasible and infeasible instances, and 200 feasible simultaneous compound-disruption cases. We compare LLM-Z3 full replanning, IPyHOPPER hierarchical repair, and an iTIMO local-revision adapter across effectiveness, plan stability, and computational cost. LLM-Z3 with Gemini achieved the highest observed compound-disruption success. IPyHOPPER nearly matched that configuration's single-disruption overall success, while preserving substantially more of the accepted itinerary on successful repairs. Successful hierarchical and local repairs made fewer edits and retained more accepted commitments than full replanning. Computational profiles differed: IPyHOPPER used no LLM inference, the evaluated LLM-Z3 adapter used compact one-call inference, and the iTIMO adapter consumed substantially more tokens. The study provides practical guidelines for balancing feasibility recovery, commitment preservation, and computational cost within evaluated settings.

Author Affiliations

Xiaofei Yuan
Euler AI
Yan Zhang
Euler AI
Shaobo Qiao
Euler AI
Huangleshuai He
University of New South Wales
Leyan Ni
University of New South Wales
Mingchen Ju
Euler AI
Lujia Yang
University of Sydney
Sijia Xu
University of New South Wales
Yifu Tang
Vecton AI
Zhengyi Yang
University of Sydney

BibTeX

@misc{yuan2026replan,
  title = {Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions},
  author = {Xiaofei Yuan and Yan Zhang and Shaobo Qiao and Huangleshuai He and Leyan Ni and Mingchen Ju and Lujia Yang and Sijia Xu and Yifu Tang and Zhengyi Yang},
  year = {2026},
  eprint = {2609.19654},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2609.19654}
}