1 citations · 1 across the 5 of their papers we have counts for
5 papers
AgentLogs: A Dataset for Opening the Black Box of Cloud Agents on GitHub
Jonan Richards, Kosei Horikawa, Youmei Fan +2
Coding agents now complete development tasks in real software projects and submit the results as pull requests. A pull request shows the outcome of an agent's execution but not the…
No Two Developers Think Alike: How Problem-Solving Styles and Experience Shape Needs in Conversational Interaction with Copilot
Jonan Richards, Bruno Alves de Oliveira, Iury Oliveira +2
Conversational LLM-based ``programming assistants'' provide a range of benefits to developers. However, recent studies demonstrate the variety in individual developers' needs regar…
Personalizing LLM-Based Conversational Programming Assistants
Jonan Richards
Large Language Models (LLMs) have shown much promise in powering a variety of software engineering (SE) tools. Offering natural language as an intuitive interaction mechanism, LLMs…
Bridging HCI and AI Research for the Evaluation of Conversational SE Assistants
Jonan Richards, Mairieli Wessel
As Large Language Models (LLMs) are increasingly adopted in software engineering, recently in the form of conversational assistants, ensuring these technologies align with develope…
What You Need is What You Get: Theory of Mind for an LLM-Based Code Understanding Assistant
Jonan Richards, Mairieli Wessel
A growing number of tools have used Large Language Models (LLMs) to support developers' code understanding. However, developers still face several barriers to using such tools, inc…