Related papers: Instruction Adherence in Coding Agent Configuratio…
Context: Changing a software application with many build-time configuration settings may introduce unexpected side-effects. For example, a change intended to be specific to a platform (e.g., Windows) or product configuration (e.g.,…
We study whether adoption of an AI coding assistant causally expands the technological frontier of individual software developers. We exploit the staggered rollout of Claude Code across GitHub between May 2025 and January 2026 in a panel of…
Large language models are increasingly used for code generation and debugging, but their outputs can still contain bugs, that originate from training data. Distinguishing whether an LLM prefers correct code, or a familiar incorrect version…
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code…
Web agents have demonstrated strong performance on a wide range of web-based tasks. However, existing research on the effect of environmental variation has mostly focused on robustness to adversarial attacks, with less attention to agents'…
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key to this process are agent manifests, configuration files…
Function calling is a core capability of large language models, essential for AI agents. Existing benchmarks such as the Berkeley Function Calling Leaderboard (BFCL), tau^2-Bench (arXiv:2506.07982), and ACEBench (arXiv:2501.12851) evaluate…
Context: Software programs can be written in different but functionally equivalent ways. Even though previous research has compared specific formatting elements to find out which alternatives affect code legibility, seeing the bigger…
Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…
Two binary instrumental variables (IVs) are nested if individuals who comply under one binary IV also comply under the other. This situation often arises when the two IVs represent different intensities of encouragement or discouragement to…
Our brain learns to update its mental model of the environment by abstracting sensory experiences for adaptation and survival. Learning to categorize sounds is one essential abstracting process for high-level human cognition, such as speech…
Successful HPC software applications are long-lived. When ported across machines and their compilers, these applications often produce different numerical results, many of which are unacceptable. Such variability is also a concern while…
Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…
Set and multiset variables in constraint programming have typically been represented using subset bounds. However, this is a weak representation that neglects potentially useful information about a set such as its cardinality. For set…
Many techniques were proposed for detecting software misconfigurations in cloud systems and for diagnosing unintended behavior caused by such misconfigurations. Detection and diagnosis are steps in the right direction: misconfigurations…
We investigate whether progressive data scheduling -- a curriculum learning strategy that incrementally increases training data exposure (33\%$\rightarrow$67\%$\rightarrow$100\%) -- yields consistent efficiency gains across architecturally…
Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand. They are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks…
File systems play an essential role in modern society for managing precious data. To meet diverse needs, they often support many configuration parameters. Such flexibility comes at the price of additional complexity which can lead to subtle…
It is commonly accepted that the quality of requirements specifications impacts subsequent software engineering activities. However, we still lack empirical evidence to support organizations in deciding whether their requirements are good…
Online convex optimization (OCO) with time-varying constraints is a critical framework for sequential decision-making in dynamic networked systems, where learners must minimize cumulative loss while satisfying regions of feasibility that…