paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Direct Manipulation and Natural Language Programming, Together at Last?

直接操作与自然语言编程,终能兼得?
OOPSLA 10(OOPSLA2)2026匹配度 3/10 · 论文属于自然语言编程与程序编辑环境的交叉,涉及 LLM 约束解码,但核心是 HCI/编程系统研究,不涉及静态分析、形式化验证、浮点程序分析、贝叶斯程序分析或 Agentic 程序分析,与用户当前研究方向仅有较弱的 PL+LLM 交集。引用 0 inbox
Parker Ziegler, David Minh-Duy Cao, Justin Lubin, Sarah E. Chasins
crossref: 2026-10-02

AI 速览

一句话:提出以编辑语言为共享接口、结合直接操作与自然语言的编程框架,并实证发现用户仍偏好直接操作。

编程语言研究已提出直接操作、结构编辑与自动重构等超越文本修改的编辑方式,但自然语言编程的兴起强化了“程序即文本”的观点。本文提出统一框架,把程序视为结构化编辑序列,以编辑语言作为直接操作与自然语言的共享接口,并用约束解码支持自然语言生成编辑;框架在 cartokit DM+NL 中实现。作者以被试内研究(N=18)比较两种模态单独与组合使用,发现两者均可用时参与者压倒性选择直接操作,仅 6.14% 编辑经由自然语言完成。主题分析显示,直接操作促进任务分解与增量编辑,并缓解自然语言编程中理解模型能力与解释生成代码的困难;自然语言主要用于自动化、参数化与重放重复编辑。

问题
自然语言编程的兴起强化了程序即文本、编辑即文本转换的观点,而直接操作、结构编辑等超越文本的编辑范式与之割裂;如何构建统一支持多种编辑范式的编程系统尚不明确。
方法
将程序视为结构化编辑序列,以编辑语言作为直接操作与自然语言交互的共享接口,并用约束解码让自然语言生成合法编辑;据此实现 cartokit 的直接操作编程系统变体 cartokit DM+NL。
评估
通过 18 名参与者的被试内研究,比较直接操作、自然语言及两者结合三种条件下的编程过程,并对会话进行主题分析。
原文摘要(Abstract)

Decades of programming languages research has contributed novel approaches to program editing that go beyond modifying text, including direct manipulation programming, structure editing, and automated refactoring tools. However, the rapid growth of natural language programming largely reinforces a view of programs as text and program editing as (unstructured) text transformation. How can we develop unified programming systems that bridge the gap between these approaches, supporting multiple editing paradigms in concert? And how would such systems change the way we program? We take a first step toward answering these questions by introducing a framework that enables program editing via both direct manipulation and natural language, and instantiate this framework in a variant of the cartokit direct manipulation programming system ( cartokit DM+NL ). Our key insight is to treat programs as sequences of structured edits and to use an edit language as a shared interface for both direct manipulation and natural language interactions, leveraging constrained decoding to support the latter. Using our instantiation, we conducted a within-subjects study ( N =18) to understand how the combination of direct manipulation and natural language as editing modalities changes the programming process compared to each modality alone. Perhaps surprisingly, we found that study participants overwhelmingly chose to edit via direct manipulation when both modalities were available, performing just 6.14% of edits via natural language. Our thematic analysis of study sessions revealed that direct manipulation aided task decomposition, encouraged incremental editing, and helped mitigate known challenges in natural language programming related to understanding model capabilities and interpreting model-generated code. Conversely, natural language editing came into play largely to automate, parameterize, and replay known edits that would otherwise be repeated tediously by hand. Our edit-based framework and study findings lay out a possible pathway for future research on programming systems that blend natural language with alternative editing modalities, building on the foundation of edit languages.

链接与引用

DOI 原文 · PDF(开放获取) ·

BibTeX
@article{paperbot12093,
  title = {Direct Manipulation and Natural Language Programming, Together at Last?},
  author = {Parker Ziegler and David Minh-Duy Cao and Justin Lubin and Sarah E. Chasins},
  journal = {Proceedings of the ACM on Programming Languages},
  volume = {10},
  number = {OOPSLA2},
  year = {2026},
  doi = {10.1145/3839487}
}