Search papers, labs, and topics across Lattice.
3
0
7
LLM multi-agent systems can achieve significantly higher accuracy at a fraction of the cost by learning to selectively delegate tasks instead of relying on rigid orchestration.
Forget fixed residual connections: Attention Residuals let each layer selectively attend to previous layers, boosting performance and gradient flow in deep LLMs.
Ditch the black-box reward function: this new rubric-based RL framework uses LLMs to judge responses against interpretable criteria, offering a more robust and transparent approach to alignment.
