Related papers: Theory of Code Space: Do Code Agents Understand So…
Recent advances in coding agents have made them capable of planning, editing, running, and testing complex code bases. Despite their growing ability in coding tasks, these systems still struggle to infer and track user intent, especially…
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code…
As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced,…
The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks…
Over-reliance on AI systems can undermine users' critical thinking and promote complacency, a risk intensified by the emergence of agentic AI systems that operate with minimal human involvement. In software engineering, agentic coding…
Code search is a widely used technique by developers during software development. It provides semantically similar implementations from a large code corpus to developers based on their queries. Existing techniques leverage deep learning…
Understanding software design practice is critical to understanding modern information systems development. New developments in empirical software engineering, information systems design science and the interdisciplinary design literature…
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…
This review presents a comprehensive analysis of two emerging paradigms in AI-assisted software development: vibe coding and agentic coding. While both leverage large language models (LLMs), they differ fundamentally in autonomy,…
Large language models (LLMs) have achieved remarkable progress in code generation, yet their true programming competence remains underexplored. We introduce the Code Triangle framework, which systematically evaluates LLMs across three…
A key feature of collaboration in science and software development is to have a {\em log} of what and how is being done - for private use and reuse and for sharing selected parts with collaborators, which most often today are distributed…
The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute to real-world projects. Their growing…
Recent advances in agentic AI have led to systems capable of autonomous task execution and language-based reasoning, yet their spatial reasoning abilities remain limited and underexplored, largely constrained to symbolic and sequential…
This paper examines how the coding strategies of sighted and blind programmers differ when working with audio feedback alone. The goal is to identify challenges in mixed-ability collaboration, particularly when sighted programmers work with…
AI coding assistants increasingly generate code alongside tests. How developers structure test code, whether inline with the implementation or in separate blocks, has traditionally been a matter of testing philosophy. We investigate whether…
Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…
Recently, Agentic AI has become an increasingly popular research field. However, we argue that current agent research practices lack standardization and scientific rigor, making it hard to conduct fair comparisons among methods. As a…
Programming requires much more than just writing code in a programming language. It is usually done in the context of a stateful environment, by interacting with a system through a graphical user interface. Yet, this wide space of…
The trajectory of AI development suggests that we will increasingly rely on agent-based systems composed of independently developed agents with different information, privileges, and tools. The success of these systems will critically…
AI agent systems increasingly rely on reusable non-LLM engineering infrastructure that packages tool mediation, context handling, delegation, safety control, and orchestration. Yet the architectural design decisions in this surrounding…