Letters from Future Self: Augmenting the Letter-Exchange Exercise with LLM-based Agents to Enhance Young Adults' Career Exploration

2025-02-26

AI Summary

Self-guided interventions for youth career exploration—such as the “Letter to My Future Self” exercise—face scalability challenges due to insufficient structural support. Method: This study proposes an LLM-based agent-augmented paradigm: a personalized “Future Self” agent, engineered via prompt design and human–AI collaborative interaction, to deliver dynamic, anthropomorphic real-time responses and dialogues. This approach transcends static writing by pioneering embodied LLM simulation of a future self for psychological intervention. Contribution/Results: A one-week controlled experiment (N=36) demonstrates that the LLM agent significantly enhances participant engagement and achieves efficacy comparable to manual letter-writing on key outcomes—including future orientation, vocational self-concept, and perceived psychological support—without requiring expert facilitation. The framework offers a scalable, low-barrier digital intervention for career development.

Technology Category

• Multiagent Systems: Agent Communication
• Intelligent Robots: Embodied AI
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Young adults often encounter challenges in career exploration. Self-guided interventions, such as the letter-exchange exercise, where participants envision and adopt the perspective of their future selves by exchanging letters with their envisioned future selves, can support career development. However, the broader adoption of such interventions may be limited without structured guidance. To address this, we integrated Large Language Model (LLM)-based agents that simulate participants' future selves into the letter-exchange exercise and evaluated their effectiveness. A one-week experiment (N=36) compared three conditions: (1) participants manually writing replies to themselves from the perspective of their future selves (baseline), (2) future-self agents generating letters to participants, and (3) future-self agents engaging in chat conversations with participants. Results indicated that exchanging letters with future-self agents enhanced participants' engagement during the exercise, while overall benefits of the intervention on future orientation, career self-concept, and psychological support remained comparable across conditions. We discuss design implications for AI-augmented interventions for supporting young adults' career exploration.

Problem

• Enhancing career exploration for young adults
• Integrating LLM-based agents in letter-exchange
• Evaluating effectiveness of AI-augmented interventions

Innovation

• LLM-based agents simulation
• Future-self letter exchange
• AI-augmented career exploration