Agents and tool calling
A model does not have to answer in one shot. It can think, call a tool, look at the result and think again.
1 steps
55 XP
A free account is needed
Start the lesson →
Sources
- Yao, S. et al. 2023 · ReAct: Synergizing Reasoning and Acting in Language Models · ICLR 2023
- Schick, T. et al. 2023 · Toolformer: Language Models Can Teach Themselves to Use Tools · NeurIPS 2023
- Anthropic 2024 · Building Effective Agents · anthropic.com/engineering
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons