The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
Human-in-the-loop software development agents,
5 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
5
Pith papers citing it
1
external citations · external index
citation-role summary
background 3
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
ACE-Bench is an execution-free benchmark that scores LLM coding agents on correct Azure SDK usage via deterministic regex checks and reference-based LLM judges derived from official documentation.
A four-dimension classifier routes agentic coding tasks into HITL, human-over-the-loop, or automated-with-monitoring tiers, analytically estimated to keep ~91% of ungoverned coding velocity under regulatory constraints.
Introduces a migration framework and A/B/C taxonomy to convert static expert LLM workflows into self-evolution-ready harnesses.
The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.
citing papers explorer
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
-
ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness
ACE-Bench is an execution-free benchmark that scores LLM coding agents on correct Azure SDK usage via deterministic regex checks and reference-based LLM judges derived from official documentation.
-
Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains
A four-dimension classifier routes agentic coding tasks into HITL, human-over-the-loop, or automated-with-monitoring tiers, analytically estimated to keep ~91% of ungoverned coding velocity under regulatory constraints.
-
Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines
Introduces a migration framework and A/B/C taxonomy to convert static expert LLM workflows into self-evolution-ready harnesses.
-
Rethinking Agentic Reinforcement Learning In Large Language Models
The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.