Related papers: Debug Smarter, Not Harder: AI Agents for Error Res…

Computational notebooks became indispensable tools for research-related development, offering unprecedented interactivity and flexibility in the development process. However, these benefits come at the cost of reproducibility and an…

Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI…

Computational notebooks, while essential for data science, are limited by their one-dimensional interface, which poorly aligns with non-linear developer workflows and complicates collaboration and human-AI interaction. In this work, we…

While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…

To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…

Saving, or checkpointing, intermediate results during interactive data exploration can potentially boost user productivity. However, existing studies on this topic are limited, as they primarily rely on small-scale experiments with human…

Autonomous agents for automated program repair represent a promising frontier in software engineering, yet their effectiveness is often hindered by reliance on post-mortem, coarse-grained execution feedback. While integrating traditional…

The massive trend of integrating data-driven AI capabilities into traditional software systems is rising new intriguing challenges. One of such challenges is achieving a smooth transition from the explorative phase of Machine Learning…

Using multiple agents was found to improve the debugging capabilities of Large Language Models. However, increasing the number of LLM-agents has several drawbacks such as increasing the running costs and rising the risk for the agents to…

As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can…

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

AI-powered code assistants, such as Copilot, are quickly becoming a ubiquitous component of contemporary coding contexts. Among these environments, computational notebooks, such as Jupyter, are of particular interest as they provide rich…

Reproducing computational research is often assumed to be as simple as rerunning the original code with provided data. In practice, missing packages, fragile file paths, version conflicts, or incomplete logic frequently cause analyses to…

Computational thinking, and by extension, computer programming, is notoriously challenging to learn. Conversational agents and generative artificial intelligence (genAI) have the potential to facilitate this learning process by offering…

Developers now have access to a growing array of increasingly autonomous AI tools for software development. While many studies examine copilots that provide chat assistance or code completions, evaluations of coding agents -- which can…

Neuroscience data are highly fragmented across labs, formats, and experimental paradigms, and reuse often requires substantial manual effort. A persistent roadblock to data reuse and integration is the need to decipher bespoke and diverse…

The introduction of large language models ignited great retooling and rethinking of the software development models. The ensuing response of software engineering research yielded a massive body of tools and approaches. In this paper, we…

Computational notebooks -- such as Jupyter or Colab -- combine text and data analysis code. They have become ubiquitous in the world of data science and exploratory data analysis. Since these notebooks present a different programming…

We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S…