References from the Context Composition Deep Research Report
Deduplicated reference list extracted from the citations used in the report. Total: 78 references.
| 1 | Vendor docs | Anthropic | How Claude remembers your project - Claude Code Docs | https://docs.anthropic.com/en/docs/claude-code/memory |
| 2 | Vendor docs | Anthropic | Create custom subagents - Claude Code Docs | https://docs.anthropic.com/en/docs/claude-code/sub-agents |
| 3 | Vendor docs | Anthropic | Agent SDK overview - Claude Code Docs | https://docs.anthropic.com/en/docs/claude-code/sdk |
| 4 | Vendor engineering | Anthropic | Effective context engineering for AI agents | https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents |
| 5 | Vendor docs | OpenAI | Agents SDK - OpenAI API | https://developers.openai.com/api/docs/guides/agents |
| 6 | Vendor docs | OpenAI | Conversation state - OpenAI API | https://developers.openai.com/api/docs/guides/conversation-state |
| 7 | Vendor docs | OpenAI | Prompt caching - OpenAI API | https://developers.openai.com/api/docs/guides/prompt-caching |
| 8 | Vendor docs | OpenAI | Using tools - OpenAI API | https://developers.openai.com/api/docs/guides/tools |
| 9 | Vendor docs | OpenAI | MCP and Connectors - OpenAI API | https://developers.openai.com/api/docs/guides/tools-connectors-mcp |
| 10 | Vendor docs | OpenAI | Skills - OpenAI API | https://developers.openai.com/api/docs/guides/tools-skills |
| 11 | Vendor docs | OpenAI | Compaction - OpenAI API | https://developers.openai.com/api/docs/guides/compaction |
| 12 | Vendor engineering | OpenAI | Using skills to accelerate OSS maintenance | https://developers.openai.com/blog/skills-agents-sdk |
| 13 | Vendor engineering | OpenAI | Shell + Skills + Compaction: Tips for long-running agents | https://developers.openai.com/blog/skills-shell-tips |
| 14 | Vendor docs | Agent Development Kit - Gemini Enterprise Agent Platform | https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/adk | |
| 15 | Vendor docs | Gemini Enterprise Agent Platform | https://docs.cloud.google.com/gemini-enterprise-agent-platform | |
| 16 | Vendor docs | State - Agent Development Kit (ADK) | https://adk.dev/sessions/state/ | |
| 17 | Vendor docs | Set up Memory Bank - Gemini Enterprise Agent Platform | https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/memory-bank/setup | |
| 18 | Vendor docs | Agent Registry - Gemini Enterprise Agent Platform | https://docs.cloud.google.com/gemini-enterprise-agent-platform/govern/agent-registry | |
| 19 | Vendor docs | Use the Agent Platform remote MCP server | https://docs.cloud.google.com/gemini-enterprise-agent-platform/reference/use-agent-platform-mcp | |
| 20 | Vendor docs | Meta | Get started with Meta Model API | https://ai.developer.meta.com/docs/getting-started/overview |
| 21 | Vendor docs | Meta | Tool calling with Llama API | https://llama.developer.meta.com/docs/guides/tool-guide/ |
| 22 | Vendor docs | Meta | OpenAI compatibility - Llama API | https://llama.developer.meta.com/docs/features/compatibility/ |
| 23 | Vendor docs | Meta | JSON Structured Output - Llama API | https://llama.developer.meta.com/docs/features/structured-output/ |
| 24 | Vendor docs | Microsoft | Microsoft Agent Framework Overview | https://learn.microsoft.com/en-us/agent-framework/overview/ |
| 25 | Vendor docs | Microsoft | Step 4: Memory & Persistence | https://learn.microsoft.com/en-us/agent-framework/get-started/memory |
| 26 | Vendor docs | Microsoft | Orchestrate agent behavior with generative AI - Copilot Studio | https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-generative-actions |
| 27 | Vendor docs | Microsoft | Multi-agent orchestration patterns and best practices - Copilot Studio | https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/multi-agent-patterns |
| 28 | Framework docs | Pydantic | Pydantic AI overview | https://pydantic.dev/docs/ai/overview/ |
| 29 | Framework docs | Pydantic | Capabilities - Pydantic AI | https://pydantic.dev/docs/ai/core-concepts/capabilities/ |
| 30 | Framework docs | Pydantic | Durable execution overview - Pydantic AI | https://pydantic.dev/docs/ai/integrations/durable_execution/overview/ |
| 31 | Framework docs | Pydantic | MCP overview - Pydantic AI | https://pydantic.dev/docs/ai/mcp/overview/ |
| 32 | Framework docs | Pydantic | Multi-Agent Patterns - Pydantic AI | https://pydantic.dev/docs/ai/guides/multi-agent-applications/ |
| 33 | Framework docs | OpenCode | Rules - OpenCode | https://opencode.ai/docs/rules/ |
| 34 | Framework docs | OpenCode | Commands - OpenCode | https://opencode.ai/docs/commands/ |
| 35 | Framework docs | OpenCode | Config - OpenCode | https://opencode.ai/docs/config/ |
| 36 | Framework docs | OpenCode | Custom Tools - OpenCode | https://opencode.ai/docs/custom-tools/ |
| 37 | Framework docs | OpenCode | Providers - OpenCode | https://opencode.ai/docs/providers/ |
| 38 | Framework docs | OpenCode | References - OpenCode | https://opencode.ai/docs/references/ |
| 39 | Framework docs | LangChain / LangGraph | LangGraph overview | https://docs.langchain.com/oss/python/langgraph/overview |
| 40 | Framework docs | LangChain / LangGraph | Persistence - LangGraph | https://docs.langchain.com/oss/python/langgraph/persistence |
| 41 | Framework docs | LangChain / LangGraph | Long-term memory - LangChain | https://docs.langchain.com/oss/python/langchain/long-term-memory |
| 42 | Framework docs | LangChain / LangGraph | Memory overview - LangChain | https://docs.langchain.com/oss/python/concepts/memory |
| 43 | Framework docs | LangChain / LangGraph | Memory - Deep Agents | https://docs.langchain.com/oss/python/deepagents/memory |
| 44 | Framework docs | LlamaIndex | Memory - LlamaIndex | https://developers.llamaindex.ai/python/framework/module_guides/deploying/agents/memory/ |
| 45 | Framework docs | LlamaIndex | Agent Workflows - LlamaIndex | https://developers.llamaindex.ai/typescript/framework/modules/agents/agent_workflow/ |
| 46 | Framework docs | CrewAI | CrewAI Documentation | https://docs.crewai.com/ |
| 47 | Repository | CrewAI | crewAIInc/crewAI | https://github.com/crewaiinc/crewai |
| 48 | Framework docs | Hugging Face | smolagents | https://huggingface.co/docs/smolagents/en/index |
| 49 | Framework docs | Hugging Face | Agents - smolagents | https://huggingface.co/docs/smolagents/en/reference/agents |
| 50 | Protocol / standard | Model Context Protocol | MCP Specification 2025-06-18 | https://modelcontextprotocol.io/specification/2025-06-18 |
| 51 | Protocol / standard | Model Context Protocol | MCP Resources specification | https://modelcontextprotocol.io/specification/2025-06-18/server/resources |
| 52 | Protocol / standard | A2A | A2A Protocol | https://a2a-protocol.org/latest/ |
| 53 | Protocol / standard | A2A | What is A2A? | https://a2a-protocol.org/latest/topics/what-is-a2a/ |
| 54 | Protocol / standard | A2A | Agent Discovery | https://a2a-protocol.org/latest/topics/agent-discovery/ |
| 55 | Research paper | Yao et al. | ReAct: Synergizing Reasoning and Acting in Language Models | https://arxiv.org/abs/2210.03629 |
| 56 | Research paper | Schick et al. | Language Models Can Teach Themselves to Use Tools (Toolformer) | https://arxiv.org/abs/2302.04761 |
| 57 | Research paper | Park et al. | Generative Agents: Interactive Simulacra of Human Behavior | https://arxiv.org/abs/2304.03442 |
| 58 | Research paper | Shinn et al. | Reflexion: Language Agents with Verbal Reinforcement Learning | https://openreview.net/forum?id=vAElhFcKW6 |
| 59 | Research paper | Wang et al. | Voyager: An Open-Ended Embodied Agent with Large Language Models | https://arxiv.org/abs/2305.16291 |
| 60 | Research paper | Packer et al. | MemGPT: Towards LLMs as Operating Systems | https://arxiv.org/abs/2310.08560 |
| 61 | Research paper | Sarthi et al. | RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval | https://arxiv.org/abs/2401.18059 |
| 62 | Research paper | Edge et al. | A Graph RAG Approach to Query-Focused Summarization | https://arxiv.org/abs/2404.16130 |
| 63 | Research paper | Gutiérrez et al. | HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models | https://arxiv.org/html/2405.14831v2 |
| 64 | Research paper | Gutiérrez et al. | From RAG to Memory: Non-Parametric Continual Learning for Large Language Models (HippoRAG 2) | https://arxiv.org/abs/2502.14802 |
| 65 | Survey | Huang et al. | Understanding the planning of LLM agents: A survey | https://arxiv.org/abs/2402.02716 |
| 66 | Research paper / benchmark | Maharana et al. | Evaluating Very Long-Term Conversational Memory of LLM Agents (LoCoMo) | https://arxiv.org/abs/2402.17753 |
| 67 | Research paper / benchmark | Wu et al. | LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory | https://arxiv.org/abs/2410.10813 |
| 68 | Survey | Luo et al. | Large Language Model Agent: A Survey on Methodology, Applications and Challenges | https://arxiv.org/abs/2503.21460 |
| 69 | Survey | Hu et al. | Memory in the Age of AI Agents | https://arxiv.org/abs/2512.13564 |
| 70 | Survey | Luo et al. | A Survey on the Evolution of LLM Agent Memory: Mechanism, Optimization, and Evaluation | https://arxiv.org/abs/2605.06716 |
| 71 | Research paper | Authors as listed on arXiv | MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models | https://arxiv.org/html/2505.22101v1 |
| 72 | Research paper | Authors as listed on arXiv | Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents | https://arxiv.org/html/2604.15877 |
| 73 | Research paper | Authors as listed on arXiv | Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory | https://arxiv.org/html/2606.10677v1 |
| 74 | Research paper / benchmark | Wu et al. | LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues | https://arxiv.org/abs/2605.12493 |
| 75 | Security research | Authors as listed on arXiv | A Systematic Study of Memory Poisoning Attacks in LLM Agents | https://arxiv.org/html/2606.04329v1 |
| 76 | Security research | Authors as listed on arXiv | MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning | https://arxiv.org/html/2605.26154v1 |
| 77 | Security research | Authors as listed on arXiv | Memory Control Flow Attacks on LLM Agents | https://arxiv.org/html/2603.15125v3 |
| 78 | Survey / security | Authors as listed on arXiv | A Survey on the Security of Long-Term Memory in LLM Agents | https://arxiv.org/html/2604.16548v1 |