Related papers: Lore: Repurposing Git Commit Messages as a Structu…
This essay proposes and explores the concept of Collage for the design of AI writing tools, transferred from avant-garde literature with four facets: 1) fragmenting text in writing interfaces, 2) juxtaposing voices (content vs command), 3)…
Recommender systems trained on offline historical user behaviors are embracing conversational techniques to online query user preference. Unlike prior conversational recommendation approaches that systemically combine conversational and…
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic…
Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods have been proposed to accelerate the inefficient token-level reasoning chain. We notice that…
Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool…
Developers and data scientists often struggle to write command-line inputs, even though graphical interfaces or tools like ChatGPT can assist. The solution? "ai-cli," an open-source system inspired by GitHub Copilot that converts natural…
T-Reqs is a text-based requirements management solution based on the git version control system. It combines useful conventions, templates and helper scripts with powerful existing solutions from the git ecosystem and provides a working…
Engineering managers increasingly must decide how to introduce generative artificial intelligence (AI), retrieval-augmented generation, and coding agents into high-risk operational functions without weakening accountability, privacy, cost…
Large language models can recognize when they are being evaluated (evaluation awareness) and behave differently because of that, which undermines the validity of safety and alignment benchmarks. We propose LURE (Live-Usage Replay…
Despite the widespread use of LLMs due to their superior performance in various tasks, their high computational costs often lead potential users to opt for the pretraining-finetuning pipeline. However, biases prevalent in manually…
Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise…
While we do not always use words, communicating what we want to an AI is a conversation -- with ourselves as well as with it, a recurring loop with optional steps depending on the complexity of the situation and our request. Any given…
In 2025, coding agents have seen a very rapid adoption. Coding agents leverage Large Language Models (LLMs) in ways that are markedly different from LLM-based code completion, making their study critical. Moreover, unlike LLM-based…
Code Search is a key task that many programmers often have to perform while developing solutions to problems. Current methodologies suffer from an inability to perform accurately on prompts that contain some ambiguity or ones that require…
As software systems grow in complexity, they must satisfy an increasing number of competing quality attributes, making it essential to balance them in a principled manner -- for example, a safety requirement for sensor-fusion verification…
Autonomous AI agents are transforming software development and redefining how developers collaborate with AI. Prior research shows that the adoption and use of AI-powered tools differ between core and peripheral developers. However, it…
With the increasing commoditization of computer vision, speech recognition and machine translation systems and the widespread deployment of learning-based back-end technologies such as digital advertising and intelligent infrastructures, AI…
Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA tickets, developer discussions, and GitHub pull requests (PRs). To address this challenge, we…
Data from software repositories have become an important foundation for the empirical study of software engineering processes. A recurring theme in the repository mining literature is the inference of developer networks capturing e.g.…
Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…