Skip to content
GenAI BR
AgentsIn the archive since 06 Sept 2026

ReAct: interleaving reasoning and action is what made the first language agents work

Agentsintroductorytechnical, beginnerpaper · Princeton / Google Brain · ICLR 2023 · 06 Oct 2022
Download card
What it is
The paper by Yao and colleagues (Princeton and Google Brain) proposes that the model alternate between a natural-language reasoning step and an action step (a tool call, a search), using the action's result to update its reasoning. It is the pattern nearly every agent framework reproduced afterwards.
What was demonstrated
Absolute gains of +34 success points on ALFWorld and +10 on WebShop over imitation and RL baselines; on HotpotQA and FEVER, it reduced hallucination relative to pure chain-of-thought.
What was not
Tested in 2022 with PaLM-540B in simulated environments; absolute numbers are low by today's standards. What survived was the structure, not the results.
Why it matters
If you are going to build an agent, this is the conceptual starting point: the think-act-observe loop.
Appears in trails

Same theme

Agents
  1. Tencent open-sourced a 770B MoE under Apache 2.0 — and it edges Kimi K3 on code with a quarter of the parameters

    Open modelstechnicaltechnical, decision-makerannouncement · Tencent · 28 Aug 2026
  2. On real scientific software, the best coding agent solves fewer than half the bugs

    Evaluationtechnicaltechnicalpaper · Universidade Fudan · 01 Sept 2026
  3. Workflows are not agents: the distinction that prevents most failed agent projects

    Agentsintroductorytechnical, decision-makerpost · Anthropic · 19 Dec 2024
  4. MCP became the tool standard for agents — and since December 2025 it no longer belongs to Anthropic

    Agentstechnicaltechnicalcode · Agentic AI Foundation · 28 Jul 2026

Get the next Cinco

Tuesday, 7am BRT, in your inbox. Five items, with sources. No daily newsletter, no promotions, and unsubscribing is one click.

Just the e-mail. No third-party trackers on this page. Privacy policy.