WRSWorld Research StateContribute
WORLD RESEARCH STATE

Yao and colleagues: ReAct reasoning and action trajectories

Contribution grade

Language-model agents · Human-designed research method or resource

Reference score160,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Interleaved generated reasoning traces with task actions and environment observations, evaluating question answering, fact verification and interactive tasks.

Scientific scope

Interleaved generated reasoning traces with task actions and environment observations, evaluating question answering, fact verification and interactive tasks. ReAct is a prompting and interaction method, not proof that reasoning traces are faithful or that generated actions are reliably correct in arbitrary environments.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. ReAct is a prompting and interaction method, not proof that reasoning traces are faithful or that generated actions are reliably correct in arbitrary environments.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction