Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences ♢ University of California
2
0
6
LLM agents can dynamically evolve their skill libraries, preventing obsolescence and improving long-horizon task performance by up to 7.8% through a fitness-driven lifecycle.
Forget expensive retraining: PromptCD unlocks significant improvements in LLM alignment and VLM visual grounding simply by contrasting model responses to cleverly designed prompts at test time.
