AI Tour Meeting: Group Travel Planning by LLM Agents

Daisuke Kikuta
7/21/2026
cs.AIcs.CLcs.MA

No official code found. Best implementation: ntt-dkiku/ai-tour-meeting (1 star, last commit 2026-07-22).

Abstract

This paper proposes AI Tour Meeting, a group travel planning framework powered by multiple Large Language Model (LLM)-based agents. The agents are instantiated with distinct personas and collaboratively seek an itinerary that satisfies their constraints and preferences through natural language discussion. The framework enables easy and flexible orchestration of such discussions by providing interfaces for configuring agent personas, discussion workflows, monitoring, and LLM deployment. Its primary use case is a simulation tool for analyzing the behavior of multiple LLM agents during tour planning discussions. This paper demonstrates the utility of the framework by presenting system validation and several analytical results obtained by the framework.

View on arXivView PDF

Code Implementations(1)

ntt-dkiku/ai-tour-meetingCommunity74%

A group travel planning framework powered by multiple LLM agents

10Jul 16, 20263 months agoNOASSERTION
ai-agents-frameworkgroup-travel-planninghuman-computer-interactionllmllm-agents+4 more

Similar Papers

Vaiage: A Multi-Agent Solution to Personalized Travel Planning

85% match2025

TravelBench: A Broader Real-World Benchmark for Multi-Turn and Tool-Using Travel Planning

83% match2025

RETAIL: Towards Real-world Travel Planning for Large Language Models

82% match1 repo22025

Developing Interactive Tourism Planning: A Dialogue Robot System Powered by a Large Language Model

82% match2023

LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis

82% match2025

TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded Reasoning

82% match2026

Cite this paper

@article{kikuta2026tour,
  title  = {AI Tour Meeting: Group Travel Planning by LLM Agents},
  author = {Daisuke Kikuta},
  year   = {2026},
  eprint = {2607.18806},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2607.18806v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2607.18806.svg)](https://codeofpaper.com/paper/2607.18806)

Discussion