UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
Read the original on arXiv Computation and Language →UnitBoost proposes a non‑generative merge operator to manage compound LLM systems, replacing the opaque higher‑level LLM that traditionally coordinates worker outputs. The operator maps worker outputs to slot‑value proposals, uses a constrained argmax to assemble the final answer, and explicitly tracks unfilled slots as residuals for subsequent rounds, thereby achieving order‑free processing and unit provenance. Across three held‑out benchmarks, UnitBoost outperforms both gold‑label‑selected candidates and input‑matched generative managers, improving compound‑system performance by up to 0.182 points and raising FanOutQA cell F1 from 0.4778 to 0.5524.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.