Related papers: Building an Internal Coding Agent at Zup: Lessons …

Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it…

Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Co-designing autonomous robotic agents involves simultaneously optimizing the controller and physical design of the agent. Its inherent bi-level optimization formulation necessitates an outer loop design optimization driven by an inner loop…

Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for…

Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code…

Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…

Code-recommendation systems, such as Copilot and CodeWhisperer, have the potential to improve programmer productivity by suggesting and auto-completing code. However, to fully realize their potential, we must understand how programmers…

Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting inside enterprise systems. Yet the tool layer on which this execution depends is still…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Automatic code generation is to generate the program code according to the given natural language description. The current mainstream approach uses neural networks to encode natural language descriptions, and output abstract syntax trees…

In several areas of knowledge, self-efficacy is related to the perfomance of individuals, including in Software Engineering. However,it is not clear how self-efficacy can be modified in training conducted by the industry. Furthermore, we…

Real-world software engineering tasks require coding agents that can operate on massive repositories, sustain long-horizon sessions, and reliably coordinate complex toolchains at test time. Existing research-grade coding agents offer…

Large Language Models (LLMs) have shown surprising proficiency in generating code snippets, promising to automate large parts of software engineering via artificial intelligence (AI). We argue that successfully deploying AI software…

Large-language-model coding tools are now mainstream in software engineering. But as these same tools move human effort up the development stack, they present fresh dangers: 10% of real prompts leak private data, 42% of generated snippets…

Generative AI (GenAI) applications are transforming software engineering by enabling automated code co-creation. However, empirical evidence on GenAI's productivity effects in industrial settings remains limited. This paper investigates the…

Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase.…

The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs,…

Code execution is a fundamental aspect of programming language semantics that reflects the exact behavior of the code. However, most pre-trained models for code intelligence ignore the execution trace and only rely on source code and…

Large Language Models (LLMs) have demonstrated considerable potential in improving coding education by providing support for code writing, explanation, and debugging. However, existing LLM-based approaches generally fail to assess students'…