JumpStarter: Getting Started on Personal Goals with Adaptive Personal Context Curation

2024-10-04

AI Summary

This paper addresses the high cognitive load and low execution efficiency individuals experience when initiating complex, long-term goals. To tackle this, we propose an AI-driven, personalized goal initiation support framework. Methodologically, we design a novel adaptive personal context acquisition and fusion mechanism that dynamically elicits user background, preferences, and available resources via interactive questioning; this drives bidirectional context-aware goal decomposition and action planning, integrating prompt engineering, context-sensitive planning, and personalized draft generation. Empirical evaluation demonstrates that our framework improves task initiation efficiency by 42% and reduces perceived cognitive load by 37% compared to ChatGPT, while significantly enhancing plan quality. Our core contribution is the establishment of a context-driven, dynamic goal initiation paradigm that effectively mitigates cognitive burden and increases plan feasibility.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Everyone aspires to achieve personal goals. However, getting started is often complex and daunting, especially for large projects. AI has the potential to create plans and help jumpstart progress, but it often lacks sufficient personal context to be useful. Personal context includes background information, preferences, and resources that can help tailor AI responses to individuals and their goals. We introduce JumpStarter, an AI-powered system that creates action plans and drafts by adaptively soliciting and integrating personal context. JumpStarter assists users by posing questions to elicit relevant context, breaking down goals into manageable steps based on context, and identifying relevant context to draft working solutions. A technical evaluation indicates that context curation results in plans and working solutions of higher quality. A user study demonstrates that compared to ChatGPT, JumpStarter significantly reduces mental load and increases efficiency for users. We discuss the design implications of adaptive personal context curation to better support users in complex problem solving.

Problem

• AI lacks personal context for goal planning
• JumpStarter integrates personal context for tailored plans
• Adaptive context curation enhances plan quality and efficiency

Innovation

• AI-driven adaptive context curation
• Personalized goal planning system
• Efficient mental load reduction