Search papers, labs, and topics across Lattice.
3
0
6
Current scientific agents struggle to maintain a coherent narrative across evidence and calculations, with only 34.81% achieving strict accuracy in complex tasks.
SCOPE-Router not only outperforms existing VLM routing methods but does so while integrating cost considerations, redefining efficiency in model selection for execution-oriented tasks.
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.
