Context Engineering 2.0: The Context of Context Engineering

Paper   |   Github   |   SII Context

🚀 TL;DR

• We formalize “context” and “context engineering,” situating them within a 20+ year history (from GUI-era context-aware systems to agentic LLM systems).
• We frame the evolution across eras:
  CE 1.0 (primitive computing) → 2.0 (intelligent agents) → 3.0 (human-level) → 4.0 (superhuman).
• Core idea: context engineering can be seen as a process of entropy reduction — transforming high-entropy human/environmental signals into low-entropy machine-interpretable representations.

---

🌐 Related Blogs

• Manus | Context Engineering for AI Agents: Lessons from Building Manus

• Anthropic | How we built our multi-agent research system

• Anthropic | Effective context engineering for AI agents

• Anthropic | Building agents with the Claude Agent SDK

• Anthropic | Writing effective tools for agents — with agents

• Anthropic | How we built our multi-agent research system

• Anthropic | Building effective agents

• Cognition | Don’t Build Multi-Agents

• Letta | Anatomy of a Context Window: A Guide to Context Engineering

• Letta | Agent Memory: How to Build Agents that Learn and Remember

• Letta | Memory Blocks: The Key to Agentic Context Management

• Letta | RAG is not Agent Memory

• LangChain | The rise of "context engineering"

• LangChain | Context Engineering

• LangChain | Agent Middleware

• LangChain | Context Engineering for Agents

• Tongyi | Tongyi Deep Research

• Github | Context Engineering Resources

• Github | 12 Factor Agents: Principles for building reliable LLM applications

• Context Engineering for Agents

• Context Engineering Guide

• Context Rot: How Increasing Input Tokens Impacts LLM Performance

• How to Fix Your Context

• What is Context Engineering and How It Differs from Prompt Engineering

• Context Engineering with Agents using LangGraph: A Guide for Modern AI Development

• Context Engineering Skills

• Context Engineering - What it is, and techniques to consider

🎤 Talks & Discussions

• Andrej Karpathy on X: "+1 for "context engineering" over "prompt engineering"

• Tobi Lutke tweet

• Free ~14 minute talk on Context Engineering tips & tricks

• Windsurf: Windsurf’s context retrieval

• CodeRabbit: Context Engineering

• Context engineering, clearly explained!

• Context Engineering for PMs

• How to build a context engineering workflow

• Context Engineering for Agents - Lance Martin, LangChain

• Context Engineering with DSPy - the fully hands-on Basics to Pro course

📚 Papers

Era 1.0

• Towards a Better Understanding of Context and Context-Awareness, Dey et al.,
• A Conceptual Framework and a Toolkit for Supporting the Rapid Prototyping of Context-Aware Applications, Dey et al.,
• Context-Aware Computing Applications, Schilit et al.,
• The Computer for the 21st Century, Weiser et al.,
• The active badge location system, Want et al.,
• ContextAdapter: Dynamic cross-system context translation for heterogeneous agents, Zhang et al.,
• Towards a better understanding of context and context-awareness, Abowd et al.,
• Pervasive computing: Vision and challenges, Satyanarayanan et al.,
• A survey of mobile phone sensing, Lane et al.,
• Sensing meets mobile social networks: The design, implementation and evaluation of the cenceme application, Miluzzo et al.,

Era 2.0

• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing, Liu et al.,
• A Survey of Context Engineering for Large Language Models, Mei et al.,
• AgentFold: Long-Horizon Web Agents with Proactive Context Management, Ye et al.,
• MemGPT: Towards LLMs as Operating Systems, Packer et al.,
• MEM0: Building Production-Ready AI Agents with Scalable Long-Term Memory, Chhikara et al.,
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents, Zhou et al.,
• Memos: A memory os for ai system, Li et al.,
• Exit: Context-aware extractive compression for enhancing retrieval-augmented generation, Hwang et al.,
• Prompt compression with context-aware sentence encoding for fast and improved LLM inference, Liskavets et al.,
• LLM4Tag: Automatic tagging system for information retrieval via large language models, Tang et al.,
• LIFT: Improving long context understanding of large language models through long input fine-tuning, Mao et al.,
• GILL: Generative image-to-language and language-to-image pretraining for unified vision-language understanding and generation, Shen et al.,
• PromptCap: Prompt-guided zero-shot image captioning, Wang et al.,
• Kosmos-2: Grounded language-image-action models for vision, language, and action, Huang et al.,
• Perceiver: General perception with iterative attention, Jaegle et al.,
• RA-CM3: Retrieval-augmented contextual multimodal models, Wang et al.,
• MemGPT-Vision: Salience-guided memory for multimodal agents, Xu et al.,
• UI-TARS: Pioneering automated GUI interaction with native agents, Qin et al.,
• Learning to synergize memory and reasoning for efficient long-horizon agents, Xu et al.,
• ChatDev: Collaborative software development with LLM agents, Li et al.,
• MEMOS: An operating system for memory-augmented generation in large language models, Han et al.,
• A-Mem: Agentic memory for LLM agents, Chen et al.,
• ContextAdapter: Dynamic cross-system context translation for heterogeneous agents, Zhang et al.,
• SharedRep: A standardized context representation for multi-platform AI integration, Garcia et al.,
• CAIM: Development and evaluation of a cognitive AI memory, Westhäuser et al.,
• Pretraining context compressor for large language models, Dai et al.,
• Prompt compression with context-aware sentence encoding for fast and improved LLM inference, Liskavets et al.,
• Kosmos-3: Scaling cross-modal alignment with temporal fusion layers, Li et al.,
• BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation, Li et al.,
• Flamingo: A visual language model for few-shot learning, Alayrac et al.,
• HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing, He et al.,
• Task memory engine: Spatial memory for robust multi-step LLM agents, Ye et al.,
• G-memory: Tracing hierarchical memory for multi-agent systems, Zhang et al.,
• Long-term memory: The foundation of AI self-evolution, Jin et al.,
• Large language models empower personalized valuation in auction, Sun et al.,
• Tree of thoughts: Deliberate problem solving with large language models, Yao et al.,
• Flexible brain–computer interfaces, Tang et al.,
• A memristor-based adaptive neuromorphic decoder for brain–computer interfaces, Liu et al.,
• Non-invasive brain-computer interfaces: state of the art and trends, Edelman et al.,
• Affective brain–computer interfaces (abcis): A tutorial, Wu et al.,
• Retrieval augmented generation (rag) and beyond: A comprehensive survey on how to make your llms use external data more wisely, Zhao et al.,
• Evolution and prospects of foundation models: From large language models to large multimodal models, Chen et al.,
• Survey on explainable AI: From approaches, limitations and applications aspects, Yang et al.,
• Large language models and knowledge graphs: Opportunities and challenges, Pan et al.,
• Mamba: Linear-time sequence modeling with selective state spaces, Gu et al.,
• LongMamba: Enhancing Mamba for long context tasks, Ye et al.,
• Locost: Long context, sparse transformers, Le Bronnec et al.,

🔒 Public Contents Policy

• The full LaTeX sources and complete paper are now public.
• You are welcome to read, share, and cite the work.
• Community feedback, issues, and PRs for corrections or improvements to the source are encouraged.

---