#官方与工程资料
- Anthropic: Building Effective AI Agents
- Anthropic: Writing tools for agents
- OpenAI Agents SDK Overview
- OpenAI Agents
- OpenAI Handoffs
- OpenAI Context Management
- OpenAI Sessions
- OpenAI Tracing
- OpenAI Safety in building agents
- OpenAI Agent evals
- OpenAI Evaluation best practices
- OpenAI Models
- OpenAI Model selection principles
- OpenAI Fine-tuning / optimization guides
- OpenAI Latency optimization
- OpenAI Streaming responses
- OpenAI Realtime WebRTC
- OpenAI Realtime WebSocket
- OpenAI Realtime server controls
- LangGraph Persistence
- LangGraph Interrupts
- Model Context Protocol
- A2A Protocol
- gRPC
- CloudEvents
#架构与业务建模资料
- Microsoft: Use Domain Analysis to Model Microservices
- Microsoft: Designing a microservice domain model
- Martin Fowler: Ubiquitous Language
- Martin Fowler: Bounded Context
#方法与研究资料
- ReAct
- Toolformer
- Reflexion
- AutoGen
- A survey on large language model based autonomous agents
- WebShop
- WebArena
- AgentBench
- SWE-bench
- AgentBoard
- OSWorld
- Autonomous chemical research with large language models
- Augmenting large language models with chemistry tools
- Evaluating large language model workflows in clinical decision support for triage and referral and diagnosis
- An autonomous agentic workflow for clinical detection of cognitive concerns using large language models