latent-collaboration-multiagent

【效率与协作】Enable LLM agents to collaborate entirely in latent space by sharing layer-wise KV cache representations instead of text, achieving 4× speedup and 71-84% fewer output tokens while maintaining 14.6% higher accuracy through lossless information preservation in continuous embeddings.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准