Search papers, labs, and topics across Lattice.
3
1
5
7
No single AI model dominates across all professional industries, revealing distinct occupational capability profiles and highlighting the need for specialized AI development.
Training web agents in a simulator can now match real-world performance: Qwen3-14B, fine-tuned with WebWorld-synthesized trajectories, rivals GPT-4o on WebArena.
ToolRMs drastically improve tool-use accuracy in LLMs, outperforming existing models by up to 17.94%, while also reducing output token usage by over 66% through efficient inference-time scaling.
