一句话：提出 Tether，一个基于 LLM 的桌面助手，为患 ADHD 的软件工程师提供自适应、情境感知的实时专注支持。
软件工程中的公平、多样与包容常忽视神经多样性，尤其是患注意缺陷多动障碍（ADHD）的开发者在持续注意、任务启动与自我调节方面的困难，而面向其开发工作流的工具很少。本文提出 Tether，一个由 LLM 驱动的桌面应用，结合本地活动监控、检索增强生成（RAG）与游戏化，为患 ADHD 的软件工程师提供自适应、情境感知的实时专注支持和个性化对话。系统集成操作系统级追踪以提示参与，聊天机器人利用 ADHD 特定资源生成相关回应。通过自用开展初步验证，发现迭代提示优化与 RAG 增强后上下文准确性有所提升。Tether 的独特性在于适配软件工作流与 ADHD 相关挑战。该工作尚未由目标用户评估，但为未来软件工程中的神经多样性友好工具奠定基础，并展示了 LLM 作为个性化支持系统的潜力。
Equity, diversity, and inclusion in software engineering often overlook neurodiversity, particularly the experiences of developers with Attention Deficit Hyperactivity Disorder (ADHD). Despite the growing awareness about that population in SE, few tools are designed to support their cognitive challenges (e.g., sustained attention, task initiation, self-regulation) within development workflows. We present Tether, an LLM-powered desktop application designed to support software engineers with ADHD by delivering adaptive, context-aware assistance. Drawing from engineering research methodology, Tether combines local activity monitoring, retrieval-augmented generation (RAG), and gamification to offer real-time focus support and personalized dialogue. The system integrates operating system level system tracking to prompt engagement and its chatbot leverages ADHD-specific resources to offer relevant responses. Preliminary validation through self-use revealed improved contextual accuracy following iterative prompt refinements and RAG enhancements. Tether differentiates itself from generic tools by being adaptable and aligned with software-specific workflows and ADHD-related challenges. While not yet evaluated by target users, this work lays the foundation for future neurodiversity-aware tools in SE and highlights the potential of LLMs as personalized support systems for underrepresented cognitive needs.
DOI 原文 ·
@inproceedings{paperbot9474,
title = {Tether: A Personalized Support Assistant for Software Engineers with ADHD},
author = {Aarsh Shah and Cleyton Magalhaes and Kiev Gama and Ronnie de Souza Santos},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00342}
}