Search papers, labs, and topics across Lattice.
2
0
5
3
LLMs can now retrieve memories like humans, using a fast familiarity check or a deliberate recollection process, leading to better personalization without overwhelming the model with irrelevant context.
LLM agents can learn to solve complex, long-horizon tasks much more effectively by using themselves as post-hoc critics to refine Q-values through hindsight reasoning.
