Raven: From Scientific Data to Trustworthy Autonomous Discovery
Year: 2026
Type: article
Abstract: Transformational AI for science will depend less on isolated model capability than on the quality of the scientific data interfaces surrounding each model. Raven is a state-aware agentic architecture for turning heterogeneous data, simulations, literature, and experiments into auditable discovery decisions. Its central design choice is to represent each step as a typed, provenance-carrying state transition and to expose local models and instruments as verifiable capabilities. A materials-discovery testbed demonstrates how domain-specific data, forward-model verification, and reinforcement learning from verifiable rewards can connect scientific data infrastructure to experimentally testable action. Raven: \url{https://ravenllm.com/}
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7212525646
FWCI:
Cites:
Cited by:
Related to: