Newshot

Software Engineering for LLM-Based Agents: A Lifecycle-Oriented Survey

Summary

arXiv:2611.23260v1 Announce Type: new Abstract: Large language model (LLM)-based Agents perform tasks through tool use and interaction with external environments. Public engineering guidance commonly begins with a target task, selects a suitable workflow or autonomous Agent design, and refines prompts, tools, and execution strategies using task outcomes, latency, and cost. When delivered as software systems, Agents must also satisfy stakeholder requirements, action boundaries, quality checks, and maintenance needs. Model-directed execution can vary across runs, failures can span model decisions and tools, and changes to prompts, models, or interfaces can affect previously accepted behavior. This survey examines how LLM-based Agents are engineered across five software lifecycle stages: Requirements Engineering, Architecture and Design, Implementation and Integration, Testing and Assurance, and Maintenance and Evolution. Based on a main collection of 355 papers, we compare the engineerin…

Original text(via arXiv cs.SE)

Computer Science > Software Engineering

Title:Software Engineering for LLM-Based Agents: A Lifecycle-Oriented Survey

Abstract:Large language model (LLM)-based Agents perform tasks through tool use and interaction with external environments. Public engineering guidance commonly begins with a target task, selects a suitable workflow or autonomous Agent design, and refines prompts, tools, and execution strategies using task outcomes, latency, and cost. When delivered as software systems, Agents must also satisfy stakeholder requirements, action boundaries, quality checks, and maintenance needs. Model-directed execution can vary across runs, failures can span model decisions and tools, and changes to prompts, models, or interfaces can affect previously accepted behavior. This survey examines how LLM-based Agents are engineered across five software lifecycle stages: Requirements Engineering, Architecture and Design, Implementation and Integration, Testing and Assurance, and Maintenance and Evolution. Based on a main collection of 355 papers, we compare the engineering problems addressed, explain how methods and practices work, and examine their reported evaluations and limitations within each stage. We synthesize how existing research supports Agent development activities and identify open problems and research directions. The result is a lifecycle-oriented reference for understanding, selecting, and further developing methods for engineering Agent software.
Comments:79 pages, 4 figures; ancillary search materials
Subjects:Software Engineering (cs.SE)
Cite as:arXiv:2611.23260 [cs.SE]
(or arXiv:2611.23260v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2611.23260 arXiv-issued DOI via DataCite

Submission history

Access Paper:

  • HTML (experimental)

Ancillary files (details):

  • search/README.md
  • search/baseline_check_271.csv
  • search/build_snapshot.py
  • search/manifest.json
  • search/queries_arxiv.json
  • search/queries_dblp.json
  • search/queries_openalex.json
  • search/queries_semantic_scholar.json
  • search/query_check_45.csv
  • search/reference_sets.csv
  • (5 additional files not shown)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.SE
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗