UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers'outputs, writes the final answer, allocates later calls, and decides when to stop. It is expressive, but it also concentrates three control decisions in an opaque, order-sensitive model call. We...
Xing Zhang, Guang-Hui Wang, Ya Cui et al.
· 0 citations