Search papers, labs, and topics across Lattice.
4
0
8
3
Frozen LLMs can autonomously achieve recursive self-improvement by learning and refining explicit, executable world models from interaction data.
Adversaries can boost their attack success rates on computer use agents from near-zero to over 28% by using a self-improving feedback loop to craft indirect prompt injections.
LLMs can achieve a 7.5x performance boost in web search and extraction by using a bi-level multi-agent architecture with iterative refinement and shared memory.
Forget rigid multi-agent pipelines: this framework lets you build self-organizing AI "companies" that dynamically recruit talent and adapt to tasks on the fly.
