Search papers, labs, and topics across Lattice.
University of Maryland
2
0
6
LLMs can't reliably predict scientific experiment outcomes, and more worryingly, they have no idea when they're wrong, unlike human experts whose accuracy skyrockets when they feel confident.
Instead of imitating reflections, LLM agents can be trained to reason about action quality by rewarding correct judgments between alternative actions, leading to improved performance and generalization.
