Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
Frontier LLMs can achieve substantial recursive self-improvement, closing nearly half of the performance gap on complex benchmarks by jointly optimizing data, training, and execution harnesses within a unified, agent-native environment.
Current multimodal agents can build sophisticated perception-control pipelines but fail to reliably execute physical tasks, losing object states and mistaking unfinished goals for completion.
