Search papers, labs, and topics across Lattice.
2
0
4
5
Forget brittle orchestration layers – LLMs can internalize complex reasoning as a learnable "HeavySkill" that rivals external agentic frameworks.
LLMs can learn to reason *worse* from seemingly better training data: models trained on CoT data with lower loss can generalize poorly due to inheriting inefficient, divergent reasoning patterns.
