LLMilestonesA milestone timeline of AI and large language models

Act II · Scaling up

PaperPrinceton / Google

ReAct: reasoning and acting together

Interleaves reasoning steps with actions such as searching or calling tools, then keeps thinking based on the results.

Why it matters

The basic loop behind today's agents: think, act, observe, think again.

Built on

Chain-of-Thought

Led to

Computer UseManus

Source: arxiv.org ↗

See it on the 3D timeline →