mlsanityData to 14 Oct 2026

Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents

arXiv 2506.20062 ↗First posted 24 Jun 2025cs.HC cs.AIcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

AI-powered code assistants are widely used to generate code completions, significantly boosting developer productivity. However, these tools typically present suggestions without explaining their rationale, leaving their decision-making process inscrutable. This opacity hinders developers' ability to critically evaluate outputs, form accurate mental models, and calibrate trust in the system. To address this, we introduce CopilotLens, a novel interactive framework that reframes code completion from a simple suggestion into a transparent, explainable interaction. CopilotLens operates as an explanation layer that reconstructs the AI agent's "thought process" through a dynamic, two-level interface. The tool aims to surface both high-level code changes and the specific codebase context influences. This paper presents the design and rationale of CopilotLens, offering a concrete framework and articulating expectations on deepening comprehension and calibrated trust, which we plan to evaluate in subsequent work.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 35 of its 58 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

35 of 58 references.

References · 35

  1. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  3. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  4. 2019Attention is not Explanationcited by 929
  5. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
  6. 2023Explainability for Large Language Models: A Surveycited by 333
  7. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 218
  8. 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 129
  9. 2022Explanations Can Reduce Overreliance on AI Systems During Decision-Makingcited by 111
  10. 2023The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Developmentcited by 96
  11. 2022Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programmingcited by 91
  12. 2024CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needscited by 84
23 more
  1. 2023A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challengescited by 75
  2. 2023"It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmerscited by 64
  3. 2022Investigating Explainability of Generative AI for Code through Scenario-based Designcited by 47
  4. 2021Perfection Not Required? Human-AI Partnerships in Code Translationcited by 42
  5. 2023Explainable Automated Debugging via Large Language Model-driven Scientific Debuggingcited by 40
  6. 2025Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistenciescited by 39
  7. 2023Investigating and Designing for Trust in AI-powered Code Generation Toolscited by 34
  8. 2023RELIC: Investigating Large Language Model Responses using Self-Consistencycited by 23
  9. 2024The Future of AI-Driven Software Engineeringcited by 23
  10. 2023Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completionscited by 20
  11. 2023Impact of Guidance and Interaction Strategies for LLM Use on Learner Performance and Perceptioncited by 19
  12. 2024Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprisecited by 17
  13. 2024Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learningcited by 16
  14. 2024Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skillscited by 14
  15. 2024BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebookscited by 12
  16. 2024HILL: A Hallucination Identifier for Large Language Modelscited by 11
  17. 2025Towards an Understanding of Context Utilization in Code Intelligencecited by 10
  18. 2023Validating AI-Generated Code with Live Programmingcited by 8
  19. 2024Assessing AI-Based Code Assistants in Method Generation Taskscited by 5
  20. 2024LLM Attributor: Interactive Visual Attribution for LLM Generationcited by 5
  21. 2025Human-AI Experience in Integrated Development Environments: A Systematic Literature Reviewcited by 5
  22. 2024Integrating Personalized Parsons Problems with Multi-Level Textual Explanations to Scaffold Code Writingcited by 2
  23. 2024Code Compass: A Study on the Challenges of Navigating Unfamiliar Codebasescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows
  2. 2026Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering Methodology
  3. 2026Latent Programming Horizons in Coding Agents
  4. 2026Vibe-GUIDE: A Graph-based User Interface in IDEs for Oversight in Vibe Coding
  5. 2026Understanding the Architecture of Coding Agents: An Exploratory Study Using a Research Prototype
  6. 2026Humans are Missing from AI Coding Agent Research
  7. 2026ExplainBench: Evaluating Code Explanations from Agents
  8. 2026From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software