一句话：提出混合人机代码导览系统 Lacy，把专家指导沉淀为可复用导览，显著提升新人代码理解效果。
软件组织普遍面临上手难题：新人需理解复杂代码库、弥补文档不足，而专家现场讲解成本高、重复且难以规模化。Lacy 是一个混合人机（human-AI）上手系统，将专家指导捕获为可复用的代码导览（code tours），把 AI 生成内容与专家策划相结合，并提供语音转导览、理解测验、播客与仪表盘等功能；其设计基于与 Beko 为期一年产学合作中 20 余次会议、问卷与访谈提炼的需求。作者在 Beko 生产环境部署 Lacy，并在 3 万行以上遗留财务系统上开展对照研究：使用专家导览的学习者测验得分达 83%，纯 AI 导览组仅 57%；学习者更偏好导览而非传统自学，并报告所需专家咨询更少，专家也认为制作导览比现场讲解负担更轻。Beko 已将 Lacy 用于组织级 onboarding，作者公开代码与研究工具包。
Every software organization faces the onboarding challenge: helping newcomers navigate complex codebases, compensate for insufficient documentation, and comprehend code they did not author. Expert walkthroughs are among the most effective forms of support, yet they are expensive, repetitive, and do not scale. We present Lacy, a hybrid human-AI onboarding system that captures expert mentoring in reusable code tours—to our knowledge, the first hybrid approach combining AI-generated content with expert curation in code tours. Our design is grounded in requirements derived from 20+ meetings, surveys, and interviews across a year-long industry partnership with Beko. Supporting features include Voice-to-Tour capture, comprehension quizzes, podcasts, and a dashboard. We deployed Lacy on Beko's production environment and conducted a controlled study on a legacy finance system (30K+ LOC). Learners using expert-guided tours achieved 83% quiz scores versus 57% for AI-only tours, preferred tours over traditional self-study, and reported they would need fewer expert consultations. Experts found tour creation less burdensome than live walkthroughs. Beko has since adopted Lacy for organizational onboarding, and we release our code and study instruments as a replication package.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2603-25391,
title = {LACY: Simulating Expert Mentoring for Software Onboarding with Code Tours},
author = {Zeynep Begüm Kara and Aytekin İsmail and Ece Ateş and İzgi Nur Tamcı and Zehra İyigün and Selin Şirin Aslangül and Ömercan Devran and Baykal Mehmet Uçar and Eray Tüzün},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805218}
}