Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
MBZUAI
4
0
10
3
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.
Automating peer review to survive the flood of AI-generated papers creates an exploitable adversarial loop, incentivizing authors to game predictable evaluators and ultimately corrupting the downstream corpus used to train future frontier models.
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.
Despite architectural differences, language models exhibit convergent evolution by learning similar periodic features for number representation, but achieving geometric separability depends on subtle training factors.