A new empirical study evaluates different methods for revising travel itineraries when disruptions occur, such as flight cancellations or hotel unavailability. The research compares full replanning using LLM-Z3 with Gemini, hierarchical plan repair with IPyHOPPER, and local revision with an iTIMO adapter. LLM-Z3 with Gemini showed the highest success rate for complex, simultaneous disruptions, while IPyHOPPER was effective for single disruptions and preserved more of the original itinerary. The study offers guidance on balancing itinerary recovery, commitment preservation, and computational cost. AI
影响 This research provides insights into optimizing AI agent performance for complex planning and revision tasks, potentially improving efficiency in logistics and travel planning.
排序理由 The cluster is an academic paper evaluating AI methods for a specific task. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- Gemini
- Gotit.pub
- Hugging Face
- Influence Flower
- IPyHOPPER
- Litmaps
- LLM-Z3
- ScienceCast
- scite Smart Citations
- Trek Bicycle Corporation
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
