UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model

arXiv cs.AISeptember 10, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.09815v1 Announce Type: new Abstract: 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 ask whether the manager needs to be generative at all. UnitBoost replaces that model with a defined meta-level operator: a task-given unit map turns worker outputs into slot-value proposals, a constrained argmax assembles the output, and the slots left unfilled or unsupported become an explicit residual for the next round. The op

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Agenter