Related papers: Context-Augmented Code Generation: How Product Con…
Code-generating tools are increasingly used in software development, yet experience reports on conversational "vibe coding" under production constraints remain limited. This paper presents an experience report from a small full-stack team…
The performance of automatic code documentation generation models depends critically on the quality of the training data used for supervision. However, most existing code documentation datasets are constructed through large scale scraping…
Recent advancements in AI and edge computing have accelerated the development of machine-centric applications (MCAs), such as smart surveillance systems. In these applications, video cameras and sensors offload inference tasks like license…
Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including…
Objective. To explore how novice programmers' trust in Artificial Intelligence-driven Development Environments (AIDEs) relates to their coding performance and AI compliance while programming under time pressure. Background. Computer…
AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…
Code review is a cornerstone of software quality assurance, and recent advances in Large Language Models (LLMs) have shown promise in its automation. However, existing benchmarks for LLM-based code review face three major limitations. Lack…
Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not…
AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite…
In this paper, we present a novel approach to improving software quality and efficiency through a Large Language Model (LLM)-based model designed to review code and identify potential issues. Our proposed LLM-based AI agent model is trained…
In this paper, we present a comparative study of five autonomous coding agents using AIDev-pop, which is a public dataset containing thousands of AI-generated pull requests (PRs) across popular open-source repositories. We evaluate agents'…
Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and…
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…
Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios…
Data wrangling, the process of preparing raw data for further analysis in computational notebooks, is a crucial yet time-consuming step in data science. Code generation has the potential to automate the data wrangling process to reduce…
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, a gap remains between their output and the problem-solving strategies of human developers. Unlike humans, who spend substantial time…
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…
Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers, and…
Generative AI is reshaping product design practices through "vibe coding," where product team members express intent in natural language and AI translates it into functional prototypes and code. Despite rapid adoption, little research has…
Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing…