Related papers: Instruction Adherence in Coding Agent Configuratio…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…
Although software managers are generally good at new project estimation, their experience of scheduling rework tends to be poor. Inconsistent or incorrect effort estimation can increase the risk that the completion time for a project will…
Federated learning (FL) under data heterogeneity remains challenging: existing methods either ignore client differences (FedAvg), require costly cluster discovery (IFCA), or maintain per-client models (Ditto). All degrade when data is…
Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…
Manual code reviews and static code analyzers are the traditional mechanisms to verify if source code complies with coding policies. However, these mechanisms are hard to scale. We formulate code compliance assessment as a machine learning…
Context: Several studies investigated the impact of anti-patterns (i.e., "poor" solutions to recurring design problems) during maintenance activities and reported that anti-patterns significantly affect the developers' effort required to…
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation,…
Binary code analysis plays an essential role in cybersecurity, facilitating reverse engineering to reveal the inner workings of programs in the absence of source code. Traditional approaches, such as static and dynamic analysis, extract…
We report a systematic failure mode in predictive representation learning. Across 2695 neural network configurations trained to predict linear-Gaussian dynamics, the optimal encoder tracks the environment rather than the system it is meant…
Reliable handling of code diffs is central to agents that edit and refactor repositories at scale. We introduce Diff-XYZ, a compact benchmark for code-diff understanding with three supervised tasks: apply (old code $+$ diff $\rightarrow$…
We consider the problem of learning the causal MAG of a system from observational data in the presence of latent variables and selection bias. Constraint-based methods are one of the main approaches for solving this problem, but the…
Misconfigurations have become the dominant causes of software failures in recent years, drawing tremendous attention for their increasing prevalence and severity. Configuration constraints can preemptively avoid misconfiguration by defining…
Every natural text is written in some style. Style is formed by a complex combination of different stylistic factors, including formality markers, emotions, metaphors, etc. One cannot form a complete understanding of a text without…
Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. Drawing on sequence-based intrusion…
Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value…
Context: Code coverage is widely used as a software quality assurance measure. However, its effect, and specifically the advisable dose, are disputed in both the research and engineering communities. Prior work reports only correlational…
Compliance as code is an emerging idea about automating compliance through programmed compliance controls and checks. Given scant existing research thus far, the paper presents an empirical analysis of a compliance as code project…
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…
Producing high-quality code is essential as it makes a codebase more maintainable, reducing the cost and effort associated with a project. However, students learning to program are often given short, automatically graded programming tasks…
Large Language Models (LLMs) are increasingly applied to real-world code generation, where functional correctness alone is insufficient for reliable deployment, developers also expect adherence to explicit requirements for robustness,…