TriFlow: A Progressive Multi-Agent Framework for Intelligent Trip Planning

TL;DR

TriFlow is a multi-agent framework that improves trip planning by combining structured reasoning and language flexibility, achieving high success rates and efficiency in complex itinerary generation.

Contribution

We introduce TriFlow, a novel multi-agent system that unifies reasoning and language models for efficient, constraint-aware trip planning.

Findings

Achieved 91.1% and 97% pass rates on benchmarks.

Over 10x runtime efficiency compared to SOTA.

Effectively handles complex constraints and personalization.

Abstract

Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints while aligning with user preferences. Existing LLM-based agents struggle with constraint satisfaction, tool coordination, and efficiency, often producing infeasible or costly plans. To address these limitations, we present TriFlow, a progressive multi-agent framework that unifies structured reasoning and language-based flexibility through a three-stage pipeline of retrieval, planning, and governance. By this design, TriFlow progressively narrows the search space, assembles constraint-consistent itineraries via rule-LLM collaboration, and performs bounded iterative refinement to ensure global feasibility and personalisation. Evaluations on TravelPlanner and TripTailor benchmarks demonstrated state-of-the-art results, achieving 91.1% and 97% final pass rates, respectively, with over 10x runtime efficiency improvement compared to current SOTA.