Exploring Interaction Patterns for Debugging: Enhancing Conversational Capabilities of AI-assistants

TL;DR

This paper introduces Robin, an enhanced AI-assistant for debugging that uses interaction patterns and conversation analysis to improve communication, fault localization, and bug resolution in developer-LLM interactions.

Contribution

The paper presents Robin, a conversational AI that leverages interaction patterns and debugging workflows to improve developer-LLM collaboration for debugging tasks.

Findings

5x improvement in bug resolution rates

Lowered conversation barriers and enhanced fault localization

Effective use of interaction patterns and debugging workflows

Abstract

The widespread availability of Large Language Models (LLMs) within Integrated Development Environments (IDEs) has led to their speedy adoption. Conversational interactions with LLMs enable programmers to obtain natural language explanations for various software development tasks. However, LLMs often leap to action without sufficient context, giving rise to implicit assumptions and inaccurate responses. Conversations between developers and LLMs are primarily structured as question-answer pairs, where the developer is responsible for asking the the right questions and sustaining conversations across multiple turns. In this paper, we draw inspiration from interaction patterns and conversation analysis -- to design Robin, an enhanced conversational AI-assistant for debugging. Through a within-subjects user study with 12 industry professionals, we find that equipping the LLM to -- (1) leverage the insert expansion interaction pattern, (2) facilitate turn-taking, and (3) utilize debugging workflows -- leads to lowered conversation barriers, effective fault localization, and 5x improvement in bug resolution rates.