Imagen de Portada

LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tang, Yongjian, Runkler, Thomas
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Agentic AI Software Engineers: Programming with Trust
por: Roychoudhury, Abhik, et al.
Publicado: (2025)

Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering
por: Li, Jingyue, et al.
Publicado: (2026)

Agentic Software Engineering: Foundational Pillars and a Research Roadmap
por: Hassan, Ahmed E., et al.
Publicado: (2025)

The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
por: Feldt, Robert, et al.
Publicado: (2026)

An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software
por: Gogani-Khiabani, Sina, et al.
Publicado: (2025)

From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability
por: De La Cruz, Elyson
Publicado: (2026)

Beyond Human-Readable: Rethinking Software Engineering Conventions for the Agentic Development Era
por: Ustynov, Dmytro
Publicado: (2026)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
por: Chen, Zhi, et al.
Publicado: (2026)

OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering
por: Imran, Mia Mohammad, et al.
Publicado: (2025)

Agentic AI for Software: thoughts from Software Engineering community
por: Roychoudhury, Abhik
Publicado: (2025)

Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning
por: Lin, Zhihao, et al.
Publicado: (2024)

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
por: Mazur, Lukasz, et al.
Publicado: (2025)

Harden and Catch for Just-in-Time Assured LLM-Based Software Testing: Open Research Challenges
por: Harman, Mark, et al.
Publicado: (2025)

Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
por: Casserini, Matteo, et al.
Publicado: (2026)

Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering
por: Benkovich, Nikita, et al.
Publicado: (2026)

Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering
por: Zhao, Zixiao, et al.
Publicado: (2026)

Automated Validation of LLM-based Evaluators for Software Engineering Artifacts
por: Fandina, Ora Nova, et al.
Publicado: (2025)

Unified Software Engineering Agent as AI Software Engineer
por: Applis, Leonhard, et al.
Publicado: (2025)

The Rise of Agentic Testing: Multi-Agent Systems for Robust Software Quality Assurance
por: Naqvi, Saba, et al.
Publicado: (2026)

The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project
por: Gröpler, Robin, et al.
Publicado: (2025)

Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
por: Rao, Hongzhou, et al.
Publicado: (2025)

Beyond Accuracy: LLM Variability in Evidence Screening for Software Engineering SLRs
por: Hida, Gilberto Sussumu, et al.
Publicado: (2026)

ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework
por: Tawosi, Vali, et al.
Publicado: (2025)

Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies
por: Angermeir, Florian, et al.
Publicado: (2025)

Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale
por: Cai, Yangxiao, et al.
Publicado: (2025)

Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
por: Salim, Mohamad, et al.
Publicado: (2026)

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
por: Trae Research Team, et al.
Publicado: (2025)

Process-Centric Analysis of Agentic Software Systems
por: Liu, Shuyang, et al.
Publicado: (2025)

Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System
por: Weiss, Martin, et al.
Publicado: (2025)

From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
por: Jin, Haolin, et al.
Publicado: (2024)

Challenges and Paths Towards AI for Software Engineering
por: Gu, Alex, et al.
Publicado: (2025)

AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering
por: Kumar, Rajesh, et al.
Publicado: (2026)

Empirical Assessment of the Perception of Software Product Line Engineering by an SME before Migrating its Code Base
por: Georges, Thomas, et al.
Publicado: (2025)

In-Context Code-Text Learning for Bimodal Software Engineering
por: Tang, Xunzhu, et al.
Publicado: (2024)

LLMs: A Game-Changer for Software Engineers?
por: Haque, Md Asraful
Publicado: (2024)

Software Performance Engineering for Foundation Model-Powered Software
por: Zhang, Haoxiang, et al.
Publicado: (2024)

Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap
por: Hassan, Ahmed E., et al.
Publicado: (2024)

Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
por: Hassan, Ahmed E., et al.
Publicado: (2024)

When Fuzzing Meets LLMs: Challenges and Opportunities
por: Jiang, Yu, et al.
Publicado: (2024)

Large Language Model-Based Agents for Software Engineering: A Survey
por: Liu, Junwei, et al.
Publicado: (2024)