mlsanityData to 7 Oct 2026

Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity

arXiv 2601.18345 ↗First posted 26 Jan 2026cs.SEcited by 6

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

Abstract (arXiv)

In 2025, coding agents have seen a very rapid adoption. Coding agents leverage Large Language Models (LLMs) in ways that are markedly different from LLM-based code completion, making their study critical. Moreover, unlike LLM-based completion, coding agents leave visible traces in software repositories, enabling the use of MSR techniques to study their impact on SE practices. This paper documents the promises, perils, and heuristics that we have gathered from studying coding agent activity on GitHub.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 63 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

21 of 63 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories23 Jun
  2. 2025Why AI Agents Still Need You: Findings from Developer-Agent Collaborations in the Wild14 Jun
  3. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  4. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair25 Mar

Other references · 17

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  3. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
  4. 2023The Impact of AI on Developer Productivity: Evidence from GitHub Copilotcited by 264
  5. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  6. 2022Do Users Write More Insecure Code with AI Assistants?cited by 186
  7. 2022Productivity Assessment of Neural Code Completioncited by 97
  8. 2025Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivitycited by 93
  9. 2022Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programmingcited by 91
  10. 2023A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challengescited by 75
  11. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 40
  12. 2024Language Models for Code Completion: A Practical Evaluationcited by 38
5 more
  1. 2023Investigating and Designing for Trust in AI-powered Code Generation Toolscited by 34
  2. 2025Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Reviewcited by 28
  3. 2024Unveiling ChatGPT's Usage in Open Source Projects: A Mining-based Studycited by 16
  4. 2023A User-centered Security Evaluation of Copilotcited by 14
  5. 2023DevGPT: Studying Developer-ChatGPT Conversationscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessionscited by 11
  2. 2026Are Coding Agents Generating Over-Mocked Tests? An Empirical Studycited by 5
  3. 2026Agentic Repository Mining: A Multi-Task Evaluationcited by 0
  4. 2026Agentic Very Much! Adoption of Coding Agent in New GitHub Projectscited by 0
  5. 2026On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplacescited by 0
  6. 2026Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure
  2. 2026Latent Programming Horizons in Coding Agents
  3. 2026Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
  4. 2025Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement
  5. 2026Agentic Much? Adoption of Coding Agents on GitHub
  6. 2026TraceLab: Characterizing Coding Agent Workloads for LLM Serving
  7. 2026A Phased Workflow for Operating LLM-Based Coding Agents
  8. 2026Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality