AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding
Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only the role of proposer. The model knows nothing of the search beyond what it is shown. As models grow more capable, a question arises...
Mahdi Farahbakhsh, I. Sela, Fatemeh Doudi et al.
· 0 citations