AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
Comparing human and llm generated code: The jury is still out!arXiv preprint arXiv:2501.16857
7 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
7
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
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.
Using a 61-feature readability model, LLM code matches or slightly exceeds human code in readability score, shows distinct issue patterns, and prompt design has limited influence.
AI-generated code requires less maintenance than human-written code, mostly involving feature additions by humans rather than bug fixes.
Comparative case study on a postgraduate Java assignment finds PureAI and PostAI projects simpler with lower code smell density than PreAI but show oversimplification and weaker responsibility separation.
Proposes and validates via feasibility study an open-source automated framework for reproducible, species-fair security comparisons of human-written, LLM-generated, and hybrid code.
The paper proposes shifting GenAI research in software engineering from narrow performance metrics to also include developer well-being, social context, and sustainable productivity.
citing papers explorer
-
AIP: A Graph Representation for Learning and Governing Agent Skills
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
-
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.
-
Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code
Using a 61-feature readability model, LLM code matches or slightly exceeds human code in readability score, shows distinct issue patterns, and prompt design has limited influence.
-
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.
-
Can LLMs Produce Better Object-Oriented Designs than Human-Involved Development?
Comparative case study on a postgraduate Java assignment finds PureAI and PostAI projects simpler with lower code smell density than PreAI but show oversimplification and weaker responsibility separation.
-
How to Compare the Security of Code Written by Humans to LLM-generated Code
Proposes and validates via feasibility study an open-source automated framework for reproducible, species-fair security comparisons of human-written, LLM-generated, and hybrid code.
-
At What Cost? Software Developers' Well-Being in the Age of GenAI
The paper proposes shifting GenAI research in software engineering from narrow performance metrics to also include developer well-being, social context, and sustainable productivity.