Related papers: Bridging the Prototype-Production Gap: A Multi-Age…
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this…
Generative AI (GenAI) has fundamentally changed how knowledge workers, such as software developers, solve tasks and collaborate to build software products. Introducing innovative tools like ChatGPT and Copilot has created new opportunities…
Traditional network experiments focus on validation through either simulation or emulation. Each approach has its own advantages and limitations. In this work, we present a new tool for next-generation network experiments created through…
Data preparation (DP) transforms raw data into a form suitable for downstream applications, typically by composing operations into executable pipelines. Building such pipelines is time-consuming and requires sophisticated programming…
Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways to construct the demonstrations used for in-context learning,…
Jupyter notebooks allow to bundle executable code with its documentation and output in one interactive environment, and they represent a popular mechanism to document and share computational workflows, including for research publications.…
Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with…
As cosmological simulations and their associated software become increasingly complex, physicists face the challenge of searching through vast amounts of literature and user manuals to extract simulation parameters from dense academic…
Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the…
Computational notebooks, tools that facilitate storytelling through exploration, data analysis, and information visualization, have become the widely accepted standard in the data science community. These notebooks have been widely adopted…
Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain,…
Chatbots have long been explored as tools to support learning, and recent advances in large language models have significantly expanded the availability of platforms for educators to author AI tutoring chatbots. Yet effective authorship…
Software developers commonly rely on platforms like Stack Overflow for problem-solving and learning. However, academic research is an untapped resource that could greatly benefit industry practitioners. The challenge lies in connecting the…
Large language models (LLMs) have shown great promise in automating data science workflows, but existing models still struggle with multi-step reasoning and tool use, which limits their effectiveness on complex data analysis tasks. To…
Large language models are redefining software engineering by implementing AI-powered techniques throughout the whole software development process, including requirement gathering, software architecture, code generation, testing, and…
Interactive notebooks are a precious tool for creating graphical user interfaces and teaching materials. Python and Jupyter are becoming increasingly popular in this context, with Jupyter widgets at the core of the interactive…
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…
Code review, which aims at ensuring the overall quality and reliability of software, is a cornerstone of software development. Unfortunately, while crucial, Code review is a labor-intensive process that the research community is looking to…
LLMs excel at code generation from English prompts, but this progress has not extended to low-resource languages. We address Bangla-to-Python code generation by introducing BanglaCodeAct, an agent-based framework that leverages multi-agent…
Jupyter notebooks are increasingly being adopted by teachers to deliver interactive practical sessions to their students. Notebooks come with many attractive features, such as the ability to combine textual explanations, multimedia content,…