Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
5
0
Effective tutoring hinges on the interplay between LLM base models and agent configurations, revealing that most combinations fail to sustain quality over time.
Forget RLHF: strategically crafted prompts alone can unlock superior math tutoring performance in LLMs, even surpassing RL-trained models.