Togedule: Scheduling Meetings with Large Language Models and Adaptive Representations of Group Availability

TL;DR

Togedule is an adaptive scheduling tool leveraging large language models to dynamically customize meeting options, reducing cognitive load and enhancing decision quality.

Contribution

The paper introduces Togedule, a novel adaptive scheduling system that uses large language models to improve meeting organization processes.

Findings

Togedule significantly reduces attendees' cognitive load.

It improves the speed of scheduling decisions.

It enhances the quality of organizer decisions.

Abstract

Scheduling is a perennial-and often challenging-problem for many groups. Existing tools are mostly static, showing an identical set of choices to everyone, regardless of the current status of attendees' inputs and preferences. In this paper, we propose Togedule, an adaptive scheduling tool that uses large language models to dynamically adjust the pool of choices and their presentation format. With the initial prototype, we conducted a formative study (N=10) and identified the potential benefits and risks of such an adaptive scheduling tool. Then, after enhancing the system, we conducted two controlled experiments, one each for attendees and organizers (total N=66). For each experiment, we compared scheduling with verbal messages, shared calendars, or Togedule. Results show that Togedule significantly reduces the cognitive load of attendees indicating their availability and improves the speed and quality of the decisions made by organizers.