# CarbonRouter preprint reports 16.1% lower emissions in conversation routing tests

_Published Tuesday, October 27, 2026 at 7:27 AM EDT · Science, AI · Latest · Tier 2 — Notable_

Researchers report that CarbonRouter reduced carbon dioxide emissions by 16.1% on average compared with FairCarbon in trace-driven experiments routing AI conversations across data centers. The preprint evaluated five language models, three GPU types and four regions using two real-world conversation datasets.

CarbonRouter accounts for the emissions from rebuilding conversation history when a query moves away from the deployment storing its reusable calculations. It selects a model, GPU type and region, and discourages moves likely to trigger another rebuild on the next turn.

Reported savings reached 23.1% for sessions longer than 30 turns. Answer quality and latency also improved, but those measures were predicted and estimated, respectively.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.35230)

---
Canonical: https://techandbusiness.org/newswire/oc27zc9_0jq4gmZqfvbRsY
Published: 2026-10-27T11:27:21.510Z
Story chronology: 2026-10-27T04:00:00.000Z
Retrieved: 2026-10-27T13:54:59.431Z
Publisher: Tech & Business (techandbusiness.org)