c-CRAB benchmark shows state-of-the-art code review agents solve only around 40% of tasks derived from human reviews, suggesting potential for human-AI collaboration.
On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 9roles
background 1polarities
background 1representative citing papers
AI agent skills are reused mainly as one-time near-verbatim copies; half stay unmodified, later maintenance is additive and local, and the behavioural contract stays almost untouched.
Probe-and-refine tuning refines AGENTS.md files using synthetic probes and improves coding agent resolve rate on SWE-bench Verified from 28.3% to 33.0% mainly by increasing coverage rather than per-patch precision.
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%.
Across 10K active GitHub projects, README.md/.gitignore/LICENSE, GitHub Actions, YAML/TOML/JSON, Dockerfiles, and AI agent files (AGENTS.md, CLAUDE.md) became dominant over 2016–2026 while Travis and XML declined.
Developers are already embedding guidance on fairness, accessibility, sustainability, tone, and privacy into repository-level files for AI agents, creating a developer-authored governance layer.
Comparative review of AI coding tool ToS shows responsibility for code quality and compliance shifted to users, with policy misalignment for autonomous agents, plus a research roadmap.
Agentic Agile-V uses Agile-V as backbone and a Specify-Constrain-Orchestrate-Prove-Evolve-Verify loop to convert AI agent conversations into traceable engineering artifacts with acceptance evidence.
ASE-26 is a proposed undergraduate curriculum for agentic software engineering organized around an evolutionary spiral of intent and build, with 21 modules and pedagogical commitments for agent-co-produced work.
citing papers explorer
-
Code Review Agent Benchmark
c-CRAB benchmark shows state-of-the-art code review agents solve only around 40% of tasks derived from human reviews, suggesting potential for human-AI collaboration.
-
From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained
AI agent skills are reused mainly as one-time near-verbatim copies; half stay unmodified, later maintenance is additive and local, and the behavioural contract stays almost untouched.
-
Probe-and-Refine Tuning of Repository Guidance for Coding Agents
Probe-and-refine tuning refines AGENTS.md files using synthetic probes and improves coding agent resolve rate on SWE-bench Verified from 28.3% to 33.0% mainly by increasing coverage rather than per-patch precision.
-
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%.
-
What's Inside a GitHub Repository? An Empirical Study on the Contents of 10K Projects
Across 10K active GitHub projects, README.md/.gitignore/LICENSE, GitHub Actions, YAML/TOML/JSON, Dockerfiles, and AI agent files (AGENTS.md, CLAUDE.md) became dominant over 2016–2026 while Travis and XML declined.
-
Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files
Developers are already embedding guidance on fairness, accessibility, sustainability, tone, and privacy into repository-level files for AI agents, creating a developer-authored governance layer.
-
Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap
Comparative review of AI coding tool ToS shows responsibility for code quality and compliance shifted to users, with policy misalignment for autonomous agents, plus a research roadmap.
-
Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
Agentic Agile-V uses Agile-V as backbone and a Specify-Constrain-Orchestrate-Prove-Evolve-Verify loop to convert AI agent conversations into traceable engineering artifacts with acceptance evidence.
-
ASE-26: a curriculum for agentic software engineering as a discipline
ASE-26 is a proposed undergraduate curriculum for agentic software engineering organized around an evolutionary spiral of intent and build, with 21 modules and pedagogical commitments for agent-co-produced work.