Search papers, labs, and topics across Lattice.
May
2
0
4
3
Multimodal agents can now continually improve their tool use and planning without parameter updates, thanks to a new framework that learns from both action-level experiences and task-level skills.
Even the best multimodal agents struggle with realistic visual scenarios, achieving only 27% accuracy on the new AgentVista benchmark that demands long-horizon tool use across web search, image search, and code.
