ReAct: Synergizing Reasoning and Acting in Language Models
by Google / Princeton · free · Last verified 2026-03-17
Introduces ReAct, a paradigm that combines reasoning traces and task-specific actions in language models. By interleaving thinking steps with tool calls, ReAct agents outperform chain-of-thought and act-only baselines on diverse tasks including question answering, fact verification, and interactive decision-making.
https://arxiv.org/abs/2210.03629 ↗B+
B+—Good
Adoption: A+Quality: A+Freshness: BCitations: A+Engagement: F
Specifications
- License
- Open Access
- Pricing
- free
- Capabilities
- reasoning, tool-use, agent-design, decision-making
- Integrations
- Use Cases
- agent-development, research, question-answering, fact-verification
- API Available
- No
- Tags
- agents, reasoning, tool-use, chain-of-thought, react
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
79Adoption
92
Quality
91
Freshness
68
Citations
96
Engagement
0
Put AI to work for your business
Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.