Related papers: Instruction Adherence in Coding Agent Configuratio…
Learning and predicting the performance of a configurable software system helps to provide better quality assurance. One important engineering decision therein is how to encode the configuration into the model built. Despite the presence of…
Consistency is one of the keys to maintainable source code and hence a successful software project. We propose a novel method of extracting the intent of programmers from source code of a large project (~300kLOC) and checking the semantic…
Labels on platforms such as GitHub support triage and coordination, yet little is known about how well they align with code modifications or how such alignment affects collaboration across contributor experience levels. We present a case…
Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize…
Estimates of heterogeneous treatment assignment effects can inform treatment decisions. Under the presence of non-adherence (e.g., patients do not adhere to their assigned treatment), both the standard backdoor adjustment (SBD) and the…
While semi-asynchronous federated learning (SAFL) combines the efficiency of synchronous training with the flexibility of asynchronous updates, it inherently suffers from participation bias, which is further exacerbated by non-IID data…
Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…
We study variable selection (also called support recovery) in high-dimensional sparse linear regression when one has external information on which variables are likely to be associated with the response. Consistent recovery is only possible…
Deep learning-based approaches for software vulnerability prediction currently mainly rely on the original text of software code as the feature of nodes in the graph of code and thus could learn a representation that is only specific to the…
Features in product lines and highly configurable systems can interact in ways that are contrary to developers' intent. Current methods to identify such unanticipated feature interactions are costly and inadequate. To address this problem…
Instruction following refers to the ability of large language models (LLMs) to generate outputs that satisfy all specified constraints. Existing research has primarily focused on constraint categories, offering limited evaluation dimensions…
Whether a file is accepted by a single parser is not a reliable indication of whether a file complies with its stated format. Bugs within both the parser and the format specification mean that a compliant file may fail to parse, or that a…
A self-adaptive system can modify its own structure and behavior at runtime based on its perception of the environment, of itself and of its requirements. To develop a self-adaptive system, software developers codify knowledge about the…
AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three…
Machine learning is increasingly permeating radio-based localization services. To keep results credible and comparable, everyday workflows should make rigorous experiment specification and exact repeatability the default, without blocking…
GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and potentially without human oversight. Like human developers, AI agents require contextual…
Testing plays an important role in securing the success of a software development project. Prior studies have demonstrated beneficial effects of applying acceptance testing within a Behavioural-Driven Development method. In this research,…
A crucial activity in software maintenance and evolution is the comprehension of the changes performed by developers, when they submit a pull request and/or perform a commit on the repository. Typically, code changes are represented in the…
Coding agents are increasingly deployed autonomously, at scale, and over long-context horizons. To be effective and safe, these agents must navigate complex trade-offs in deployment, balancing influence from the user, their learned values,…
Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to…