Search papers, labs, and topics across Lattice.
3
0
5
5
Automatic harness evolution may not be the silver bullet for LLM performance it was thought to be, often lagging behind simpler scaling methods.
Tmax sets a new standard for terminal agent performance with a surprisingly simple RL recipe that outshines larger models.
Agentic search gets a meta-RL boost: MR-Search learns to self-reflect and adapt search strategies across episodes, significantly outperforming standard RL baselines.
