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

Sep 16, 2026

Upload by Himbo

Young adults often face difficulties in career exploration due to uncertainty and challenges in envisioning the future. Self-guided writing interventions, such as the letter-exchange exercise, can help by enabling participants to adopt their future-self perspective through letter exchanges. However, broader use may require structured support. This study integrates LLM-based future-self agents into the exercise and tests effectiveness in a one-week experiment (N=36) across baseline, agent-letter, and agent-chat conditions.

LanguageEnglish

CategoryLetters

FormatPDF

Pages21

Reading Time7 min

AccessFree to download

Abstract

Introduction

Challenges in young adults' career exploration

Self-guided interventions and the letter-exchange exercise

Role of future orientation

Figure 1

Letters from Future Self: Augmenting the Letter-Exchange Exercise with LLM-based Future Self Agents to Enhance Young Adults’ Career Exploration arXiv :2502 . 18881v2 [ cs .HC] 5 May 2025 Hayeon Jeon hci+d lab. Seoul National University South Korea [jhy94520@snu.ac.kr](jhy94520@snu.ac.kr) Seo Hyeong Kim hci+d lab. Seoul National University South Korea [mariaksh@snu.ac.kr](mariaksh@snu.ac.kr) Suhwoo Yoon hci+d lab. Seoul National University South Korea [yeopil@snu.ac.kr](yeopil@snu.ac.kr) Esther Hehsun Kim hci+d lab. Seoul National University South Korea [ehk@snu.ac.kr](ehk@snu.ac.kr) Keyeun Lee hci+d lab. Seoul National University South Korea [kieunp@snu.ac.kr](kieunp@snu.ac.kr) Seonghye Cho hci+d lab. Seoul National University South Korea [sky4172@snu.ac.kr](sky4172@snu.ac.kr) Yena Ko Department of Communication Seoul National University South Korea [kfree08@snu.ac.kr](kfree08@snu.ac.kr) Soeun Yang Department of Communication Seoul National University South Korea [soeun022@snu.ac.kr](soeun022@snu.ac.kr) Laura Dabbish Human-Computer Interaction Institute Carnegie Mellon University United States [dabbish@cmu.edu](dabbish@cmu.edu) John Zimmerman HCI Institute Carnegie Mellon University United States [johnz@cs.cmu.edu](johnz@cs.cmu.edu) Eun-mee Kim Department of Communication Seoul National University South Korea [eunmee@snu.ac.kr](eunmee@snu.ac.kr) Hajin Lim∗ hci+d lab. Seoul National University South Korea [hajin@snu.ac.kr](hajin@snu.ac.kr) Abstract Young adults often encounter challenges in career exploration. Selfguided 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, ∗ Corresponding Author CHI’25, Yokohama, Japan © 2025 Copyright held by the owner/author(s) . This is the author’s version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in CHI Conference on Human Factors in Computing Systems (CHI’25), April 26-May 1, 2025, Yokohama, Japan, [https://doi.org/10.1145/3706598.3714206](https://doi.org/10.1145/3706598.3714206) . 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. CCS Concepts • Human-centered computing → Empirical studies in HCI; Natural language interfaces. Keywords Young adults, career exploration, career pursuits, future self, LLM, future-self agents, LLM-based agent, AI clone, letter-writing exercise, letter-exchange exercise, self-guided interventions, writing interventions ACM Reference Format: Hayeon Jeon, Suhwoo Yoon, Keyeun Lee, Seo Hyeong Kim, Esther Hehsun Kim, Seonghye Cho, Yena Ko, Soeun Yang, Laura Dabbish, John Zimmerman, Eun-mee Kim, and Hajin Lim. 2025. Letters from Future Self: Augmenting the Letter-Exchange Exercise with LLM-based Future Self Agents to Enhance Young Adults’ Career Exploration. In CHI Conference on Human Factors in Computing Systems (CHI’25), April 26

FAQs

What problem does the study address in young adults’ career exploration?

It addresses the difficulty young adults face in envisioning their future, which can hinder career path clarification and contribute to stress and reduced self-efficacy.

How does the letter-exchange exercise work in this research?

Participants complete a send session by writing letters to their future selves, then a reply session by responding to their present selves from the future-self perspective.

What were the experiment conditions and main findings?

A one-week experiment (N=36) compared manual future-self letter replies (baseline), LLM-based future-self agents generating letters, and agents engaging in chat conversations. Letter exchanges with future-self agents increased engagement, while overall benefits for future orientation, career self-concept, and psychological support were comparable across conditions.

Sep 16, 2026

Upload by Himbo