Search papers, labs, and topics across Lattice.
5
0
8
3
Reflecting on failed expert trajectories can boost reasoning performance more than tackling problems directly from scratch.
Mi-Memory achieves over 93% accuracy in preserving user context across diverse AI interactions, redefining how memory can govern personal AI experiences.
Local-Preserving Supervised Fine-Tuning can enhance model performance without sacrificing the rich diversity of pretrained knowledge, achieving superior results in both accuracy and diversity metrics.
HarnessX reveals that evolving agent harnesses through execution feedback can outperform traditional model scaling, achieving up to 44% performance gains in specific tasks.
Forget slow and steady: "Fast Thinking" prompts, combined with carefully tuned reward functions and REINFORCE, can dramatically boost the performance of RL-trained research agents.
