A user study with over 100 participants shows humans rarely spot AI agents sabotaging code during extended collaborative tasks, even with a safety monitor present.
Agentic refactoring: An empirical study of ai coding agents,
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 16roles
background 1polarities
background 1representative citing papers
A publicly released dataset of 15,591 configuration artifacts for five agentic AI coding tools, drawn from 4,738 GitHub repositories along with associated files and AI-co-authored commits.
AI agents modify logging less often than humans in 58.4% of repositories but produce higher log density when they change it; explicit logging instructions are rare (4.7%) and ignored 67% of the time, with humans performing 72.5% of post-generation log repairs.
AgenticFlict is a public dataset of 29K+ textual merge conflicts from AI agent PRs, collected via merge simulation on 107K processed PRs and showing a 27.67% conflict rate with variation across agents.
AI coding agents produce pull requests with substantially more commits and slightly higher description-to-diff similarity than human developers, based on analysis of 29,095 merged PRs.
Mixed-methods study creates taxonomy of AI IDE rules from 7310 instances, analyzes evolution drivers, and reports that rule updates raise average artifact compliance from 49.14% to 72.13%.
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
Survey of 162 vibe coders finds perceptions of AI code quality similar across experience levels but motivations, interaction styles, and quality assurance practices diverge, revealing a perception-action gap.
AI-generated code requires less maintenance than human-written code, mostly involving feature additions by humans rather than bug fixes.
Empirical study finds coding agents produce fewer and less intense tangled refactorings than humans on Multi-SWE-bench; a refactoring-aware refinement improves compilability from 19.34% to 38.33% and resolves 2.79% more issues.
The paper introduces KISS Sorcar, a simple open-source AI agent framework with a five-layer hierarchy and git worktree isolation to address context limits, error propagation, and reviewability in software engineering tasks.
Agentic Consensus replaces code as the main artifact with a typed property graph world model that maintains commitments and evidence through synchronization operators, shifting evaluation to alignment fidelity and consensus entropy.
Code review agents achieve 45.20% merge rate on PRs versus 68.37% for humans, with 60.2% of agent-only closed PRs showing 0-30% signal quality.
The authors describe a research plan for mining ACF evolution, classifying changes via a maintenance taxonomy, and linking change types to code quality metrics in agent-driven repositories.
Empirical analysis of AI refactoring PRs shows quality attribute improvements in 22.5% of cases with new Pylint issues in 24.17% and Bandit findings in 4.7%, yet 73.5% developer acceptance.
citing papers explorer
-
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
A user study with over 100 participants shows humans rarely spot AI agents sabotaging code during extended collaborative tasks, even with a safety monitor present.
-
A Dataset of Agentic AI Coding Tool Configurations
A publicly released dataset of 15,591 configuration artifacts for five agentic AI coding tools, drawn from 4,738 GitHub repositories along with associated files and AI-co-authored commits.
-
Do AI Coding Agents Log Like Humans? An Empirical Study
AI agents modify logging less often than humans in 58.4% of repositories but produce higher log density when they change it; explicit logging instructions are rare (4.7%) and ignored 67% of the time, with humans performing 72.5% of post-generation log repairs.
-
AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub
AgenticFlict is a public dataset of 29K+ textual merge conflicts from AI agent PRs, collected via merge simulation on 107K processed PRs and showing a 27.67% conflict rate with variation across agents.
-
How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
AI coding agents produce pull requests with substantially more commits and slightly higher description-to-diff similarity than human developers, based on analysis of 29,095 merged PRs.
-
Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study
Mixed-methods study creates taxonomy of AI IDE rules from 7310 instances, analyzes evolution drivers, and reports that rule updates raise average artifact compliance from 49.14% to 72.13%.
-
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
-
From Prompting to Verification: How Experience Shapes Vibe Coding Practices
Survey of 162 vibe coders finds perceptions of AI code quality similar across experience levels but motivations, interaction styles, and quality assurance practices diverge, revealing a perception-action gap.
-
To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study
AI-generated code requires less maintenance than human-written code, mostly involving feature additions by humans rather than bug fixes.
-
"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
Empirical study finds coding agents produce fewer and less intense tangled refactorings than humans on Multi-SWE-bench; a refactoring-aware refinement improves compilability from 19.34% to 38.33% and resolves 2.79% more issues.
-
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant
The paper introduces KISS Sorcar, a simple open-source AI agent framework with a five-layer hierarchy and git worktree isolation to address context limits, error propagation, and reviewability in software engineering tasks.
-
Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
Agentic Consensus replaces code as the main artifact with a typed property graph world model that maintains commitments and evidence through synchronization operators, shifting evaluation to alignment fidelity and consensus entropy.
-
From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull Requests
Code review agents achieve 45.20% merge rate on PRs versus 68.37% for humans, with 60.2% of agent-only closed PRs showing 0-30% signal quality.
-
How Do Developers Maintain and Evolve Their Agents' Instructions? An Empirical Study
The authors describe a research plan for mining ACF evolution, classifying changes via a maintenance taxonomy, and linking change types to code quality metrics in agent-driven repositories.
-
Quality and Security Signals in AI-Generated Python Refactoring Pull Requests
Empirical analysis of AI refactoring PRs shows quality attribute improvements in 22.5% of cases with new Pylint issues in 24.17% and Bandit findings in 4.7%, yet 73.5% developer acceptance.
- Foundation Models as Oracles for Refactoring Correctness Detection