Related papers: The Kitchen Loop: User-Spec-Driven Development for…

Traditional self-adaptive systems automatically reconfigure existing components in response to changing requirements, but provide limited support for the generation of novel functionalities. The software generation capabilities of large…

Automatic programming attempts to minimize human intervention in the generation of executable code, and has been a long-standing challenge in the software engineering community. To advance automatic programming, researchers are focusing on…

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…

Large Language Models are increasingly capable of interpreting multimodal inputs to generate complex 3D shapes, yet robust methods to evaluate geometric and structural fidelity remain underdeveloped. This paper introduces a human in the…

User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether…

Automatically generated software, especially code produced by Large Language Models (LLMs), is increasingly adopted to accelerate development and reduce manual effort. However, little is known about the long-term reliability of such systems…

Large language models are redefining software engineering by implementing AI-powered techniques throughout the whole software development process, including requirement gathering, software architecture, code generation, testing, and…

Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs benefit substantially from structured feedback, static analysis,…

Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as…

Large language models (LLMs) are remarkably good at writing code. A particularly valuable case of human-LLM collaboration is code-based UI prototyping, a method for creating interactive prototypes that allows users to view and fully engage…

Developing distributed systems presents significant challenges, primarily due to the complexity introduced by non-deterministic concurrency and faults. To address these, we propose a specification-driven development framework. Our method…

Large Language Models (LLMs) are one of the most promising developments in the field of artificial intelligence, and the software engineering community has readily noticed their potential role in the software development life-cycle.…

Natural language-driven no-code development allows users to specify software functionality using natural language (NL) instead of editing source code, promising increased productivity and democratized development. Large language models…

Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the performance of Code LLMs on a set of individual tasks, their…

Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, achieving high scores on benchmarks such as HumanEval and MBPP. However, these benchmarks primarily assess functional correctness and neglect broader…

Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approaches are not scalable, and hence, unsuitable for complex software systems. Recently, Large…

This paper presents insights from evaluating 16 frontier large language models (LLMs) on the WebApp1K benchmark, a test suite designed to assess the ability of LLMs to generate web application code. The results reveal that while all models…

We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks, where test cases serve as both prompt and verification for code generation. Unlike traditional approaches relying…

Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their behavior in structured, specification-driven processes remains poorly understood. This paper presents an empirical study design using…