Related papers: Contract-Coding: Towards Repo-Level Generation via…
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…
Historically, programming language semantics has focused on assigning a precise mathematical meaning to programs. That meaning is a function from the program's input domain to its output domain determined solely by its syntactic structure.…
Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little supervision. Although vibe coding is increasingly adopted, are its outputs really…
We present a self-certifying compiler for the COGENT systems language. COGENT is a restricted, polymorphic, higher-order, and purely functional language with linear types and without the need for a trusted runtime or garbage collector. It…
Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging,…
Building complex software systems necessitates the use of component-based architectures. In theory, of the set of components needed for a design, only some small portion of them are "custom"; the rest are reused or refactored existing…
A key challenge in System of Systems (SoS) engineering is the analysis and maintenance of global properties under SoS evolution, and the integration of new constituent elements. There is a need to model the constituent systems composing a…
Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering --…
The detection of vulnerabilities in smart contracts remains a significant challenge. While numerous tools are available for analyzing smart contracts in source code, only about 1.79% of smart contracts on Ethereum are open-source. For…
Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for…
Changes in source code are an inevitable part of software development. They are the results of indispensable activities such as fixing bugs or improving functionality. Descriptions for code changes (commit messages) help people better…
Smart contract vulnerabilities have caused billions in financial losses, raising questions about whether programming language paradigms can reduce security overhead. While imperative languages like Solidity require developers to manually…
State-of-the-art code generation frameworks rely on mental simulation, where LLMs internally trace execution to verify correctness. We expose a fundamental limitation: the Mental-Reality Gap -- where models hallucinate execution traces and…
Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints-notably generative numeracy, attribute binding, and part-level relations. To address…
Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…
The increasing proliferation of IoT devices and AI applications has created a demand for scalable and efficient computing solutions, particularly for applications requiring real-time processing. The compute continuum integrates edge and…
We present a new way of embedding functional languages into the Coq proof assistant by using meta-programming. This allows us to develop the meta-theory of the language using the deep embedding and provides a convenient way for reasoning…
With the goal of facilitating team collaboration, we propose a new approach to building vector representations of individual developers by capturing their individual contribution style, or coding style. Such representations can find use in…
State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when scaling to repository-level systems. Current workflows relying only on natural language…
AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural decisions, yet almost no one reviews them as such. We identify five mechanisms by which agents make implicit…