An Empirical Study of Developer-Provided Context for AI Coding Assistants in Open-Source Projects

• URL: http://arxiv.org/abs/2512.18925v1
• Date: Sun, 21 Dec 2025 23:51:02 GMT
• Title: An Empirical Study of Developer-Provided Context for AI Coding Assistants in Open-Source Projects
• Authors: Shaokang Jiang, Daye Nam,
• Abstract summary: This paper presents a large-scale empirical study to characterize the emerging form of developer-provided context.<n>We developed a comprehensive taxonomy of project context that developers consider essential, organized into five high-level themes.<n>Our study also explores how this context varies across different project types and programming languages.
• Score: 2.392035679895744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Large Language Models (LLMs) have demonstrated remarkable capabilities, research shows that their effectiveness depends not only on explicit prompts but also on the broader context provided. This requirement is especially pronounced in software engineering, where the goals, architecture, and collaborative conventions of an existing project play critical roles in response quality. To support this, many AI coding assistants have introduced ways for developers to author persistent, machine-readable directives that encode a project's unique constraints. Although this practice is growing, the content of these directives remains unstudied. This paper presents a large-scale empirical study to characterize this emerging form of developer-provided context. Through a qualitative analysis of 401 open-source repositories containing cursor rules, we developed a comprehensive taxonomy of project context that developers consider essential, organized into five high-level themes: Conventions, Guidelines, Project Information, LLM Directives, and Examples. Our study also explores how this context varies across different project types and programming languages, offering implications for the next generation of context-aware AI developer tools.

Related papers

• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
  Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
  arXiv  Detail & Related papers  (2026-01-15T18:55:03Z)
• Understanding the Role of Large Language Models in Software Engineering: Evidence from an Industry Survey [0.6660458629649825]
  This paper reports an empirical study of Large Language Models (LLMs) adoption in software engineering, based on a survey of 46 industry professionals.<n>Results reveal positive perceptions of LLMs, particularly regarding faster resolution of technical questions, improved documentation support, and enhanced source code standardization.<n> respondents also expressed concerns about cognitive dependence, security risks, and the potential erosion of technical autonomy.
  arXiv  Detail & Related papers  (2025-12-19T20:57:19Z)
• Learning to Code with Context: A Study-Based Approach [0.28675177318965045]
  The rapid emergence of generative AI tools is transforming the way software is developed.<n>Project-based courses offer an effective environment to explore and evaluate the integration of AI assistance into real-world development practices.<n>This paper presents our approach and a user study conducted within a university programming project in which students collaboratively developed computer games.
  arXiv  Detail & Related papers  (2025-12-04T20:40:36Z)
• Context Engineering for AI Agents in Open-Source Software [13.236926479239754]
  GenAI-based coding assistants have disrupted software development.<n>Their next generation is agent-based, operating with more autonomy and potentially without human oversight.<n>One challenge is to provide AI agents with sufficient context about the software projects they operate in.
  arXiv  Detail & Related papers  (2025-10-24T12:55:48Z)
• A Survey of Vibe Coding with Large Language Models [93.88284590533242]
  "Vibe Coding" is a development methodology where developers validate AI-generated implementations through outcome observation.<n>Despite its transformative potential, the effectiveness of this emergent paradigm remains under-explored.<n>This survey provides the first comprehensive and systematic review of Vibe Coding with large language models.
  arXiv  Detail & Related papers  (2025-10-14T11:26:56Z)
• A Survey on Code Generation with LLM-based Agents [61.474191493322415]
  Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm.<n>LLMs are characterized by three core features.<n>This paper presents a systematic survey of the field of LLM-based code generation agents.
  arXiv  Detail & Related papers  (2025-07-31T18:17:36Z)
• MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks [56.34018316319873]
  We propose MERA Code, a benchmark for evaluating code for the latest code generation LLMs in Russian.<n>This benchmark includes 11 evaluation tasks that span 8 programming languages.<n>We evaluate open LLMs and frontier API models, analyzing their limitations in terms of practical coding tasks in non-English languages.
  arXiv  Detail & Related papers  (2025-07-16T14:31:33Z)
• On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing [82.96523584351314]
  We decouple the task of context retrieval from the other components of the repository-level code editing pipelines. We conclude that while the reasoning helps to improve the precision of the gathered context, it still lacks the ability to identify its sufficiency.
  arXiv  Detail & Related papers  (2024-06-06T19:44:17Z)
• Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study [72.24266814625685]
  We explore the performance of large language models (LLMs) across the entire software development lifecycle with DevEval.<n>DevEval features four programming languages, multiple domains, high-quality data collection, and carefully designed and verified metrics for each task.<n> Empirical studies show that current LLMs, including GPT-4, fail to solve the challenges presented within DevEval.
  arXiv  Detail & Related papers  (2024-03-13T15:13:44Z)
• A Survey on Knowledge Distillation of Large Language Models [99.11900233108487]
  Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities to open-source models. This paper presents a comprehensive survey of KD's role within the realm of Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2024-02-20T16:17:37Z)
• Code Ownership in Open-Source AI Software Security [18.779538756226298]
  We use code ownership metrics to investigate the correlation with latent vulnerabilities across five prominent open-source AI software projects. The findings suggest a positive relationship between high-level ownership (characterised by a limited number of minor contributors) and a decrease in vulnerabilities. With these novel code ownership metrics, we have implemented a Python-based command-line application to aid project curators and quality assurance professionals in evaluating and benchmarking their on-site projects.
  arXiv  Detail & Related papers  (2023-12-18T00:37:29Z)
• Representation of Developer Expertise in Open Source Software [12.583969739954526]
  We use the World of Code infrastructure to extract the complete set of APIs in the files changed by open source developers. We then employ Doc2Vec embeddings for vector representations of APIs, developers, and projects. We evaluate if these embeddings reflect the postulated topology of the Skill Space.
  arXiv  Detail & Related papers  (2020-05-20T16:36:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.