# IAPO preprint reports lower token use for matching agent-system accuracy

_Published Friday, November 6, 2026 at 4:26 PM EST · AI, Science · Latest · Tier 2 — Notable_

Researchers introduced IAPO, a method for training an AI agent coordinator, and reported that its deployed plans matched the strongest comparison system's accuracy using fewer tokens. The arXiv preprint compared fifteen published multi-agent and workflow-search systems using the same 7B executor on long-input mathematics, reading and coding tasks.

IAPO trains the coordinator to account for how decisions interact, rather than crediting each decision separately. Removing that interaction term reduced coding accuracy by 7 to 17 points. The reported efficiency gains come from these benchmark comparisons.

## Sources

- [cs.LG updates on arXiv.org](https://arxiv.org/abs/2611.07495)

---
Canonical: https://techandbusiness.org/newswire/Q8_9RCqNj0JjHVjvxOMs_W
Published: 2026-11-06T21:26:38.819Z
Story chronology: 2026-11-06T05:00:00.000Z
Retrieved: 2026-11-06T22:50:26.376Z
Publisher: Tech & Business (techandbusiness.org)