Tech Meridian ← LIVE FEED
RU

RESEARCH · RESEARCH · #589

Unified empirical evaluation of travel-agent itinerary revision under resource disruptions

This arXiv preprint (arXiv:2609.19654v1) presents a systematic empirical comparison of three approaches for revising travel itineraries after resource disruptions: LLM-Z3 full replanning (with Gemini), IPyHOPPER hierarchical plan repair, and the iTIMO local-revision LLM adapter. Using two TREK-derived benchmarks (500 single-disruption cases and 200 feasible compound-disruption cases), the study evaluates effectiveness, plan stability, and computational cost, finding Gemini+LLM-Z3 best on compound disruptions, IPyHOPPER nearly matching single-disruption success while preserving more accepted commitments, and iTIMO consuming substantially more tokens.

KEY POINTS

  1. This arXiv preprint (arXiv:2609.19654v1) presents a systematic empirical comparison of three approaches for revising travel itineraries after resource disruptions: LLM-Z3 full replanning (with Gemini), IPyHOPPER hierarchical plan repair, and the iTIMO local-revision LLM adapter.
  2. Using two TREK-derived benchmarks (500 single-disruption cases and 200 feasible compound-disruption cases), the study evaluates effectiveness, plan stability, and computational cost, finding Gemini+LLM-Z3 best on compound disruptions, IPyHOPPER nearly matching single-disruption success while preserving more accepted commitments, and iTIMO consuming substantially more tokens.
  3. Quantifies practical trade-offs between full replanning, classical repair, and LLM-based adapters for itinerary recovery, guiding choices that balance feasibility, commitment preservation, and compute cost.

WHY IT MATTERS

Quantifies practical trade-offs between full replanning, classical repair, and LLM-based adapters for itinerary recovery, guiding choices that balance feasibility, commitment preservation, and compute cost.

SOURCES & TIMELINE

1