Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries
Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and refining executable solutions from verifier feedback. Methods such as TTT-Discover use test-time training (TTT) to update the solution-generating LLM from...
Chong-He Jiang, Ao Qu, Si-Yuan Liu et al.
· 0 citations