TARS is an LLM-powered agent integrated into Visual Studio Code that supports program comprehension through autonomous explanations anchored directly to the code under analysis, built around a lightweight Theory of Mind paradigm.
Abstract
Code comprehension is one of the most time-consuming tasks in software engineering, yet most LLM-based assistants produce explanations that ignore who is asking and force developers into a disruptive copy-paste workflow. We present TARS, an LLM-powered agent integrated into Visual Studio Code that supports program comprehension through autonomous explanations anchored directly to the code under analysis. Built around a lightweight Theory of Mind paradigm, TARS profiles a developer's expertise, role, and stylistic preferences, then adapts the depth and tone of its explanations accordingly, grounding them in project documentation via Retrieval-Augmented Generation. To evaluate TARS, we conducted a controlled experiment with 18 participants on non-trivial Java snippets. Participants using TARS completed tasks 26\% faster, reported lower cognitive load, and found the explanations meaningfully adapted to their profiles.
While agents aid initial task completion, they harm users' code comprehension and thus do not prepare users to extend their code, and low-effort agent interaction types, like copy+paste prompts and auto-accepted edits, are linked with lower comprehension.
Scientific research involving code has long rested on the assumption that at least one person understands why the code exists. As scientists adopt coding agents, this assumption is breaking down. Drawing on an ongoing contextual inquiry of scientific programmers working with agentic tools (four cases to date), a survey...
A rigorous comparative analysis of three popular agentic IDEs in the generation of five full-stack Web applications from scratch shows that Agentic IDEs cannot replace developers but shift their role toward building software by orchestrating LLM-based agents through natural-language instructions and iterative refinemen...
Manuel Marceca, Maria Teresa Rossi, Leonardo Mariani· 0 citations
Accountable translation is developed as an analytic framework for making consequential changes attributable, inspectable, scoped in validation, and contestable, and extends HCI accounts of traceability and end-user debugging by locating professional authority and repair rights across heterogeneous technical and organiz...
This work designed a tool called dBlocks with the following features: blocks to scope content, a context manager to edit context, and inline execution to verify code, and shows how human-centered design can guide the development of LLM-integrated tools.
This work proposes a framework for extracting reusable developer preferences from interaction traces, generates personalized skills through rule-based bootstrapping and evidence-grounded refinement, and evaluates them using a reproducible replay framework with an interactive, trajectory-conditioned LLM-based human deve...
Shuyan Huang, Kai Du, Andrew S. Lan· 3 citations· ⚡2
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
