mlsanityData to 14 Oct 2026

Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows

arXiv 2507.08149 ↗First posted 10 Jul 2025cs.SEcited by 28

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

Abstract (arXiv)

Developers now have access to a growing array of increasingly autonomous AI tools for software development. While many studies examine copilots that provide chat assistance or code completions, evaluations of coding agents -- which can automatically write files and run code -- still rely on static benchmarks. We present the first controlled study of developer interactions with coding agents, characterizing how more autonomous AI tools affect productivity and experience. We evaluate two leading copilot and agentic coding assistants, recruiting participants who regularly use the former. Our results show agents can assist developers in ways that surpass copilots (e.g., completing tasks humans may not have accomplished) and reduce the effort required to finish tasks. Yet challenges remain for broader adoption, including ensuring users adequately understand agent behaviors. Our findings reveal how workflows shift with coding agents and how interactions differ from copilots, motivating recommendations for researchers and highlighting challenges in adopting agentic systems.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. First posted on arXiv 10 Jul 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 24.

28 papers.

Sort:

By area:

  1. 2026Mind the Sim2Real Gap in User Simulation for Agentic Taskscited by 54
  2. 2025Training Proactive and Personalized LLM Agentscited by 46
  3. 2025How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupationscited by 19
  4. 2026How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessionscited by 14
  5. 2026AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Developmentcited by 11
  6. 2025Completion neq Collaboration: Scaling Collaborative Effort with Agentscited by 6
  7. 2026Position: Human-Centric AI Requires a Minimum Viable Level of Human Understandingcited by 6
  8. 2026Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agentscited by 6
  9. 2025How can we assess human-agent interactions? Case studies in software agent designcited by 4
  10. 2026Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agentscited by 3
  11. 2026Humans are Missing from AI Coding Agent Researchcited by 3
  12. 2026Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Modelcited by 3
16 more
  1. 2026Reflections and New Directions for Human-Centered Large Language Modelscited by 2
  2. 2026On the Adoption of AI Coding Agents in Open-source Android and iOS Developmentcited by 1
  3. 2026Comparing Developer and LLM Biases in Code Evaluationcited by 1
  4. 2026The Kitchen Loop: User-Spec-Driven Development for a Self-Evolving Codebasecited by 1
  5. 2026RECAP: An End-to-End Platform for Capturing, Replaying, and Analyzing AI-Assisted Programming Interactionscited by 1
  6. 2026Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Codecited by 1
  7. 2026Offloading Score: Measuring AI Reliance Through Counterfactual Workflowscited by 1
  8. 2026RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studiescited by 0
  9. 2026Human agency in initial human-AI proof formalization workflowscited by 0
  10. 2026From Conversation to Contribution: Characterizing Coding Agent in Open-Source Softwarecited by 0
  11. 2026Early Adoption of Agentic Coding Tools by GitHub Projectscited by 0
  12. 2026MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systemscited by 0
  13. 2026Generation of Web Apps with Agentic IDEs: An Empirical Assessmentcited by 0
  14. 2026VibeJam: A User Study Platform for Web Development with Agentscited by 0
  15. 2026Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semanticscited by 0
  16. 2026Does AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests
  2. 2026Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
  3. 2025Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025
  4. 2025Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support
  5. 2026From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation
  6. 2026(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding
  7. 2026Agentic Coding Needs Proactivity, Not Just Autonomy
  8. 2026Humans Integrate, Agents Fix: How Agent-Authored Pull Requests Are Referenced in Practice