Source record

Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2608.23395.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

A preregistered pilot compares one wide LLM agent, a no-orchestrator single agent, and two intermediate configurations (three to five narrow workers) on cross-border VAT determination across 4,400 runs with deterministic oracle labels. Intermediate configurations lead in accuracy, but the matched-token control fires, meaning prompt budget could explain the gap. One hallucinated schema-conforming record inverts the ordering.

A 4,400-run preregistered sweep with falsification checks and matched-token arms separates agent-count from prompt-budget effects, a control most multi-agent benchmarks skip. Useful for anyone designing orchestrated agent pipelines.

Cited by

No citations on record.