Search papers, labs, and topics across Lattice.
7
0
11
17
WebSwarm's innovative recursive delegation allows agents to not only search but also adaptively collaborate, leading to superior performance in complex web search tasks.
Major LLM failures can be traced back to specific disruptions in cognitive organization, providing a roadmap for targeted interventions and deeper understanding of model behavior.
Agents using TSR can maintain clarity in task execution, boosting success rates by up to 12 points on challenging mobile GUI tasks.
iLLaDA's fully bidirectional diffusion training outperforms traditional autoregressive models, achieving remarkable gains across key language benchmarks.
Task success rates for agentic phone use soar from 36.67% to 45.33% through a novel combination of real and mock environments in training.
LOGOS shows that a single generative model can outperform specialized systems across a range of scientific tasks, challenging the need for separate AI frameworks in the natural sciences.
Current multimodal models are stuck in bi-modal interactions, but OmniGAIA and OmniAtlas offer a path towards truly omni-modal AI assistants capable of reasoning and tool use across video, audio, and images.
