一句话：提出基于开发者 IDE 内行为进行画像，推动代码智能从通用方案走向个性化辅助。
现有代码智能系统常忽视开发者个体差异，而开发者在编码风格、工具链偏好、领域专长与问题解决策略上高度异质，统一响应对专家冗长、对新手晦涩，影响效果与采用。本文主张从“一刀切”转向“一人一策”的个性化代码智能，将开发者在 IDE 内的动态行为——代码编写模式、导航路径与调试轨迹——作为其能力与习惯的隐式表示；通过捕获和解释这些信号，可对开发者画像并据此提供辅助。摘要未报告具体评估结果，重点在于问题动机与个性化代码智能的形式化。
The rapid advancement of LLMs has opened new opportunities in automated software engineering, driving progress in code understanding, agent-based workflows, and productivity tools. However, existing code intelligence systems have largely sidelined the end-users they aim to serve—the developers themselves. Developers exhibit substantial heterogeneity across multiple dimensions: coding style, toolchain preferences, domain-specific expertise, and problem-solving strategies. Failing to account for these individual differences directly compromises both the effectiveness of code intelligence and the likelihood of its adoption. For example, a senior architect and a junior engineer ask: "Describe the authorization module." Without personalized context, the system produces a uniform response—verbose for the expert, incomprehensible for the novice. This gap motivates a fundamental shift: from one-size-fits-all to one-size-fits-one code intelligence. A developer's dynamic in-IDE behaviors—code authoring patterns, navigation pathways, debugging trajectories—implicitly encode a rich representation of their competencies and habits. If captured and interpreted systematically, these signals can enable Personalized Code Intelligence, formalized as:
@inproceedings{paperbot9861,
title = {On the Road to Personalized Code Intelligence: Portraiting and Assisting Developers Based on Their In-IDE Behaviors},
author = {Yuhong Liu and Yunhe Su and Zhipeng Peng and Zhiwen Luo and Lin Shi and Zhi Jin and Li Zhang},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3807398}
}