Imagen de Portada

Triage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality Signals

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Madeyski, Lech
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Artificial Intelligence Machine Learning D.2; I.2
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLM4SCREENLIT: Recommendations on Assessing the Performance of Large Language Models for Screening Literature in Systematic Reviews
por: Madeyski, Lech, et al.
Publicado: (2025)

Test Case Prioritization: A Snowballing Literature Review and TCPFramework with Approach Combinators
por: Chojnacki, Tomasz, et al.
Publicado: (2026)

Multicalibration for LLM-based Code Generation
por: Campos, Viola, et al.
Publicado: (2025)

The Rise and Fall(?) of Software Engineering
por: Mastropaolo, Antonio, et al.
Publicado: (2024)

Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study
por: Alshaikh, Moaath, et al.
Publicado: (2026)

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
por: Ashrafi, Nazmus
Publicado: (2026)

DeepCodeProbe: Towards Understanding What Models Trained on Code Learn
por: Majdinasab, Vahid, et al.
Publicado: (2024)

Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning
por: Puccioni, Laura, et al.
Publicado: (2025)

Aligning Programming Language and Natural Language: Exploring Design Choices in Multi-Modal Transformer-Based Embedding for Bug Localization
por: Chakraborty, Partha, et al.
Publicado: (2024)

MFH: A Multi-faceted Heuristic Algorithm Selection Approach for Software Verification
por: Su, Jie, et al.
Publicado: (2025)

CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models
por: Jin, Hangzhan, et al.
Publicado: (2025)

Morescient GAI for Software Engineering (Extended Version)
por: Kessel, Marcus, et al.
Publicado: (2024)

Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks
por: Wang, Wei, et al.
Publicado: (2024)

Assessing LLMs for Front-end Software Architecture Knowledge
por: Guerra, L. P. Franciscatto, et al.
Publicado: (2025)

Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
por: Shetty, Manish, et al.
Publicado: (2024)

The Explabox: Model-Agnostic Machine Learning Transparency & Analysis
por: Robeer, Marcel, et al.
Publicado: (2024)

Test-driven Software Experimentation with LASSO: an LLM Prompt Benchmarking Example
por: Kessel, Marcus
Publicado: (2024)

Variables are a Curse in Software Vulnerability Prediction
por: Groppe, Jinghua, et al.
Publicado: (2024)

Software Defined Vehicle Code Generation: A Few-Shot Prompting Approach
por: Nguyen, Quang-Dung, et al.
Publicado: (2025)

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
por: Trooskens, Geert, et al.
Publicado: (2026)

LLM-Driven Cost-Effective Requirements Change Impact Analysis
por: Etezadi, Romina, et al.
Publicado: (2025)

Towards a Probabilistic Framework for Analyzing and Improving LLM-Enabled Software
por: Baldonado, Juan Manuel, et al.
Publicado: (2025)

Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation
por: Jin, Kailun, et al.
Publicado: (2024)

Reinforcement Learning for Dynamic Workflow Optimization in CI/CD Pipelines
por: Soni, Aniket Abhishek, et al.
Publicado: (2026)

CoverUp: Effective High Coverage Test Generation for Python
por: Pizzorno, Juan Altmayer, et al.
Publicado: (2024)

LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study
por: Ranasinghe, Nishath Rajiv, et al.
Publicado: (2025)

CodeCompass: Navigating the Navigation Paradox in Agentic Code Intelligence
por: Paipuru, Tarakanath
Publicado: (2026)

Revisiting the Performance of Deep Learning-Based Vulnerability Detection on Realistic Datasets
por: Chakraborty, Partha, et al.
Publicado: (2024)

Code Generation for Machine Learning using Model-Driven Engineering and SysML
por: Raedler, Simon, et al.
Publicado: (2023)

Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance
por: Calboreanu, Elias
Publicado: (2026)

Leveraging Large Language Models for Use Case Model Generation from Software Requirements
por: Eisenreich, Tobias, et al.
Publicado: (2025)

DEFault++: Automated Fault Detection, Categorization, and Diagnosis for Transformer Architectures
por: Jahan, Sigma, et al.
Publicado: (2026)

A Tale of Two Systems: Characterizing Architectural Complexity on Machine Learning-Enabled Systems
por: Ferreira, Renato Cordeiro
Publicado: (2025)

A Metrics-Oriented Architectural Model to Characterize Complexity on Machine Learning-Enabled Systems
por: Ferreira, Renato Cordeiro
Publicado: (2025)

EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0
por: Costa, Igor, et al.
Publicado: (2025)

CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research
por: Savenkov, Vladislav
Publicado: (2026)

Learning Software Bug Reports: A Systematic Literature Review
por: Long, Guoming, et al.
Publicado: (2025)

Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification
por: Thompson, Kyle, et al.
Publicado: (2024)

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
por: Holt, Samuel, et al.
Publicado: (2023)

LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops
por: Ravi, Ravin, et al.
Publicado: (2026)