Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

AI Agents

LLMを使って

  1. 作業手順の推論

  2. 作業の実施

を行わせる

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

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

Generative Agents: Interactive Simulacra of Human Behavior