Search papers, labs, and topics across Lattice.
2
0
5
0
Decomposing complex tasks into verifiable checklists unlocks more effective reinforcement learning, but only if you can avoid the pitfalls of reward hacking and verifier bias.
Agentic coding gets a boost: Laguna XS.2, a 33B parameter Mixture-of-Experts model, is now available under Apache 2.0, offering a powerful and accessible tool for long-horizon tasks.
