AI Agents#
LLMを使って
作業手順の推論
作業の実施
を行わせる
LangChain#
> Entering new AgentExecutor chain...
I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.
Action: Search
Action Input: "Leo DiCaprio girlfriend"
Observation: Camila Morrone
Thought: I need to find out Camila Morrone's age
Action: Search
Action Input: "Camila Morrone age"
Observation: 25 years
Thought: I need to calculate 25 raised to the 0.43 power
Action: Calculator
Action Input: 25^0.43
Observation: Answer: 3.991298452658078
Thought: I now know the final answer
Final Answer: Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.
> Finished chain.
Auto-GPT#
Significant-Gravitas/Auto-GPT: An experimental open-source attempt to make GPT-4 fully autonomous.
もっと動的で使いやすくした感じ?
関連文献#
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
https://arxiv.org/abs/2205.00445 (2022年5月)
AIエージェントが複数のツールやアプローチを組み合わせる「MRKL(Multi-Round Knowledge Loop)」というアプローチを提案
Language Model Cascades
https://arxiv.org/abs/2207.10342 (2022年7月)
言語モデルカスケードというアイデアを提案
ReAct: Synergizing Reasoning and Acting in Language Models
https://arxiv.org/abs/2210.03629 (2022年10月)
推論(Reasoning)と行動(Action)を交互に行うReAct (Reason + Act)というアプローチを提案
Toolformer: Language Models Can Teach Themselves to Use Tools
https://arxiv.org/abs/2302.04761 (2023年2月)
外部ツールを呼び出す方法を学習した「Toolformer」というモデルの提案
Generative Agents: Interactive Simulacra of Human Behavior
https://arxiv.org/abs/2304.03442 (2023年4月)
25人のAIエージェントによる小規模社会シミュレーション