---
title: "A Survey of Context Engineering for LLMs — arXiv 2025"
url: https://stacklist.com/card/c28bf8eb-b9e7-42c6-b853-bdf655a2df52
source_url: "https://arxiv.org/abs/2507.13334"
stack: https://stacklist.com/c/technology/stack/e16dcdcb-06b9-481c-aef9-40b6d73a5c8e
summary: "This survey introduces Context Engineering as a formal discipline for systematically optimizing information payloads provided to Large Language Models during inference, presenting a comprehensive taxonomy covering context retrieval, processing, management, RAG, memory systems, and multi-agent architectures. The paper analyzes over 1,400 research papers and identifies a critical research gap between models' strong context understanding and their limited ability to generate sophisticated long-form outputs."
tags: "context-engineering, large-language-models, survey, retrieval-augmented-generation, prompt-engineering, multi-agent-systems, natural-language-processing"
key_entities: "Lingrui Mei (person), Context Engineering (concept), Large Language Models (concept), Retrieval-Augmented Generation (concept), Multi-Agent Systems (concept), Tool-Integrated Reasoning (concept), arXiv (organization), Jiayu Yao (person), Yuyao Ge (person), Jiafeng Guo (person)"
classification: "reference"
content_hash: "sha256:02c9338026ce841d92680caac61c8e2741cf09a10e793fcfefb720bbf2b5dc91"
acp_version: "0.2"
token_counts_approximate: 1174
visibility: public
agent_accessible: true
status: "final"
---

# A Survey of Context Engineering for LLMs — arXiv 2025

--> Computer Science > Computation and Language arXiv:2507.13334 (cs) [Submitted on 17 Jul 2025 ( v1 ), last revised 21 Jul 2025 (this version, v2)] Title: A Survey of Context Engineering for Large Language Models Authors: Lingrui Mei , Jiayu Yao , Yuyao Ge , Yiwei Wang , Baolong Bi , Yujun Cai , Jiazhi Liu , Mingyu Li , Zhong-Zhi Li , Duzhen Zhang , Chenlin Zhou , Jiayi Mao , Tianze Xia , Jiafeng Guo , Shenghua Liu View a PDF of the paper titled A Survey of Context Engineering for Large Language Models, by Lingrui Mei and 14 other authors View PDF HTML (experimental) Abstract: The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational components and the sophisticated implementations that integrate them into intelligent systems. We first examine the foundational components: context retrieval and generation, context processing and context management. We then explore how these components are architecturally integrated to create sophisticated system implementations: retrieval-augmented generation (RAG), memory systems and tool-integrated reasoning, and multi-agent systems. Through this systematic analysis of over 1400 research papers, our survey not only establishes a technical roadmap for the field but also reveals a critical research gap: a fundamental asymmetry exists between model capabilities. While current models, augmented by advanced context engineering, demonstrate remarkable proficiency in understanding complex contexts, they exhibit pronounced limitations in generating equally sophisticated, long-form outputs. Addressing this gap is a defining priority for future research. Ultimately, this survey provides a unified framework for both researchers and engineers advancing context-aware AI. Comments: ongoing work; 166 pages, 1411 citations Subjects: Computation and Language (cs.CL) Cite as: arXiv:2507.13334 [cs.CL]   (or arXiv:2507.13334v2 [cs.CL] for this version)   https://doi.org/10.48550/arXiv.2507.13334 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Lingrui Mei [ view email ] [v1] Thu, 17 Jul 2025 17:50:36 UTC (2,127 KB) [v2] Mon, 21 Jul 2025 17:48:18 UTC (2,132 KB) Full-text links: Access Paper: View a PDF of the paper titled A Survey of Context Engineering for Large Language Models, by Lingrui Mei and 14 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev   |   next > new | recent | 2025-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? )