relayllm-efficient-reasoning-collaboration

【效率与协作】Enable small language models to dynamically invoke larger models at critical reasoning tokens rather than offloading entire queries. RelayLLM achieves 49.52% accuracy across benchmarks while invoking the large model for only 1.07% of tokens—98.2% cost reduction compared to non-collaborative approaches.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准