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

arXiv: https://arxiv.org/abs/2609.19654 · HTML: https://mlsanity.com/paper/2609.19654/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- LLM agents and tool use

## Builds on (most cited first, 23 of 23)

- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools](https://mlsanity.com/paper/2404.11891/) (2024)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [Planning with Multi-Constraints via Collaborative Language Agents](https://mlsanity.com/paper/2405.16510/) (2024)
- [To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning](https://mlsanity.com/paper/2410.16456/) (2024)
- [TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning](https://mlsanity.com/paper/2502.20508/) (2025)
- [ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning](https://mlsanity.com/paper/2509.25586/) (2025)
- [Flex-TravelPlanner: A Benchmark for Flexible Planning with Language Agents](https://mlsanity.com/paper/2506.04649/) (2025)
- [Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving](https://mlsanity.com/paper/2511.01633/) (2025)
- [Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks](https://mlsanity.com/paper/2512.22673/) (2025)
- [Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach](https://mlsanity.com/paper/2411.14484/) (2024)
- [RETAIL: Towards Real-world Travel Planning for Large Language Models](https://mlsanity.com/paper/2508.15335/) (2025)
- [TripTide: A Benchmark for Adaptive Travel Planning under Disruptions](https://mlsanity.com/paper/2510.21329/) (2025)
- [A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning](https://mlsanity.com/paper/2601.21162/) (2026)
- [Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory](https://mlsanity.com/paper/2603.15280/) (2026)
- [Graphy'our Data: Towards End-to-End Modeling, Exploring and Generating Report from Raw Data](https://mlsanity.com/paper/2502.16868/) (2025)
- [TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents](https://mlsanity.com/paper/2606.01046/) (2026)
- [TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning](https://mlsanity.com/paper/2607.26977/) (2026)
- [HTN Plan Repair Algorithms Compared: Strengths and Weaknesses of Different Methods](https://mlsanity.com/paper/2504.16209/) (2025)
- [iTIMO: An LLM-empowered Synthesis Dataset for Travel Itinerary Modification](https://mlsanity.com/paper/2601.10609/) (2026)
- [TRACE: Tourism Recommendation with Accountable Citation Evidence](https://mlsanity.com/paper/2605.07677/) (2026)
- [RAIDS: Rethinking Data Systems as Responsible Intelligent Infrastructure](https://mlsanity.com/paper/2606.21831/) (2026)
- [HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.28351/) (2026)

## Built on by (most cited first, 1 of 1)

- [ControlScope: Workflow Revision and Reliability in LLM Agents](https://mlsanity.com/paper/2609.34313/) (2026)

## Abstract (arXiv)

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.