不同视角[11]

Source	作者	Agent = LLM + ?
1. LLM Powered Autonomous Agents	Lilian Weng	Plan + Memory + Tools
2. The Rise and Potential of Large Language ModelBased Agents: A Survey	FudanNLP	Perception + Brain + Action
3. A Survey on Large Language Model based Autonomous Agents	中国人民大学高瓴人工智能学院	Profile + Memory + Planning + Action

视角1

架构图

组件 [1]

Agent = LLM + plan[规划能力] + memory[记忆能力] +Tools[工具使用能力]

Planning [1]

Task Decomposition
- CoT
- ToT
Self-Reflection
- ReAct
- Reflexion
- Chain of Hindsight

Memory [1]

Types of Memory
- Sensory memory as learning embedding representations for raw inputs, including text, image or other modalities;
- Short-term memory as in-context learning. It is short and finite, as it is restricted by the finite context window length of Transformer.
- Long-term memory as the external vector store that the agent can attend to at query time, accessible via fast retrieval.

Tool Use [1]

让 agent 选择合适的工具 [10]
- 可以 retrieve 相关示例来做 few-shot prompt。
- 也可以进一步 fine tune 特定模型，例如之前的 Toolformer。
Research
- TALM (Tool Augmented Language Models; Parisi et al. 2022) [1]
- Toolformer (Schick et al. 2023) [1]
- Gorilla [10]
Production [1]
- ChatGPT Plugins
- OpenAI API function calling

Agentic Reasoning Design Patterns[20]