mlsanityData to 7 Oct 2026

A Survey of Context Engineering for Large Language Models

arXiv 2507.13334 ↗First posted 17 Jul 2025cs.CLcited by 120

Not on the map. Why?

Cited by 62 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 120 papers in the map (data through 7 Oct 2026). Builds on 601 of its 1,411 references that are in the map. First posted on arXiv 17 Jul 2025.

Builds on

601 of 1,411 references.

References · 601

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  8. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  10. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  11. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  12. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
38 more
  1. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  2. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  3. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  4. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  5. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  6. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  7. 2023VideoChat: Chat-Centric Video Understandingcited by 851
  8. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  9. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  10. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  11. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  12. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  13. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  14. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  15. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  16. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  17. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  18. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  19. 2024Understanding the planning of LLM agents: A surveycited by 414
  20. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  21. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 377
  22. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  23. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  24. 2024Agent Workflow Memorycited by 342
  25. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  26. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  27. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  28. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  29. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  30. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  31. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  32. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  33. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
  34. 2024Token-Budget-Aware LLM Reasoningcited by 242
  35. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 241
  36. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 236
  37. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  38. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 226

50 most cited of 601 All 601 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 39; 2026: 81.

120 papers.

Sort:

By area:

  1. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  2. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 95
  3. 2026Self-Harness: Harnesses That Improve Themselvescited by 79
  4. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  5. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Taskscited by 62
  6. 2025SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarioscited by 49
  7. 2025Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMscited by 45
  8. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 42
  9. 2025Self Speculative Decoding for Diffusion Large Language Modelscited by 29
  10. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
  11. 2025SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agentscited by 21
  12. 2025FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learningcited by 20
38 more
  1. 2026Large Language Model Reasoning Failurescited by 20
  2. 2025OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking Systemcited by 18
  3. 2026Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learnedcited by 18
  4. 2025UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalistcited by 15
  5. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  6. 2025Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalizationcited by 12
  7. 2026MemoBrain: Executive Memory as an Agentic Brain for Reasoningcited by 12
  8. 2026Self-Compacting Language Model Agentscited by 11
  9. 2025ContextNav: Towards Agentic Multimodal In-Context Learningcited by 9
  10. 2026Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scalingcited by 9
  11. 2026Towards Long-horizon Agentic Multimodal Searchcited by 9
  12. 2026From Question Answering to Task Completion: A Survey on Agent System and Harness Designcited by 9
  13. 2026PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoningcited by 9
  14. 2025Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoningcited by 8
  15. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  16. 2025ContextPilot: Fast Long-Context Inference via Context Reusecited by 8
  17. 2026Lost in the Noise: How Reasoning Models Fail with Contextual Distractorscited by 8
  18. 2026CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoningcited by 8
  19. 2026Multi-Agent Debate with Memory Maskingcited by 8
  20. 2026CL-bench Life: Can Language Models Learn from Real-Life Context?cited by 8
  21. 2026Semantic-Aware Adaptive Visual Memory for Streaming Video Understandingcited by 8
  22. 2025Agentic Services Computingcited by 6
  23. 2025Everything is Context: Agentic File System Abstraction for Context Engineeringcited by 6
  24. 2026SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMscited by 6
  25. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  26. 2025LongRM: Revealing and Unlocking the Context Boundary of Reward Modelingcited by 5
  27. 2025Agentic Systems in Radiology: Design, Applications, Evaluation, and Challengescited by 5
  28. 2025Sparser Block-Sparse Attention via Token Permutationcited by 5
  29. 2026Large Language Model Agents Are Not Always Faithful Self-Evolverscited by 5
  30. 2026VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAGcited by 5
  31. 2026What makes a harness a harness: necessary and sufficient conditions for an agent harnesscited by 5
  32. 2025Beyond Pixels: Exploring DOM Downsampling for LLM-Based Web Agentscited by 4
  33. 2025AI Propaganda factories with language modelscited by 4
  34. 2025Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideationcited by 4
  35. 2025Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluationcited by 4
  36. 2025ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replaycited by 4
  37. 2025Boosting Reasoning in Large Multimodal Models via Activation Replaycited by 4
  38. 2025HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelinescited by 4

50 most cited of 120 All 120 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
  2. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
  3. 2026ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
  4. 2025Towards more Contextual Agents: An extractor-Generator Optimization Framework
  5. 2026ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents
  6. 2026Continuum Memory Architectures for Long-Horizon LLM Agents
  7. 2025Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation
  8. 2026ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents