Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
4
0
7
8
Long-horizon agents can now recover from deep failures by maintaining a relational belief state and prospectively reasoning over repair directions, even when distilled into a 9B model.
LLMs can recursively rewrite their own solutions from specialized environments into generalizable training data, boosting performance on complex tasks by over 34% and improving pass@3 by up to 17 percentage points.
LLMs can learn to play complex games far more effectively by co-evolving a skill bank with a decision-making agent, enabling consistent long-horizon decision-making.
Stop bloating your agent's context window: a dependency-aware skill graph slashes token costs by 37% and boosts reward by 43% compared to naive skill loading.