Search papers, labs, and topics across Lattice.
5
7
7
17
DiffCold shatters the seesaw dilemma in item recommendation, enabling accurate cold-start predictions without sacrificing the performance of warm items.
LatentSkill achieves a 21.4-point increase in task success while slashing prefill token usage by over 64%, revolutionizing how LLM agents utilize skills.
Stop wasting idle compute: ProAct agents anticipate user needs and proactively gather information, slashing task completion time and hallucinations.
LLMs' final layers might be holding your recommendation system back: representations from middle layers actually perform *better*, and a modular compression approach can unlock significant gains.
Current LLM evaluation benchmarks often conflate chatbots and true AI agents, leading to misaligned research efforts, but this survey provides a framework for targeted evaluation based on environmental complexity and agent capabilities.
