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

TL;DR

This work examines whether LLM-based agents that simulate a participant's future self can augment the letter-exchange career exploration intervention for young adults. In a one-week between-subjects study (N=36), participants engaged in traditional letter replies, AI-generated letters, or AI-driven chat conversations with future selves. Results show that AI augmentation, especially the letter-based format, boosts engagement and sustains gains in future orientation, career clarity, and resilience comparably to the standard method. The study provides design implications for AI-augmented self-guided career exploration, highlighting pacing, variety of agents, and privacy considerations to balance reflection, agency, and personalization. This work advances practical guidelines for integrating LLM technologies into self-directed developmental interventions with potential applications in education and career support.

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.

Figures (9)

• Figure 1: In this work, we investigate how LLM-based future-self agents can support young adults' career exploration. Participants write letters to their future selves (left). Then, their LLM-based future-self agents reply to their letters (right).
• Figure 2: Research model overview
• Figure 3: Study procedure
• Figure 4: Template for future profile (3 years later)
• Figure 5: Instructions for two activities: (1) writing a letter to future self and (2) writing a reply to present self