# Preprint reports emotion reasoning gains from targeted prompt changes

_Published Monday, October 26, 2026 at 9:32 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report in a preprint that targeted changes to agent prompts improved multimodal emotion reasoning without updating model weights. On the MER2025 dataset, the method raised F-score by 0.6-2.2 points across four models ranging from 2B to 38B parameters, including an increase from 52.3 to 54.5 on Qwen2.5-VL-7B.

Separate agents examine visual, acoustic and textual inputs, then combine observations into an emotion assessment with supporting citations. A verification stage checks evidence and identifies which component caused an error, generating prompt changes accepted only after validation on a held-out set. The gains were measured against a frozen static pipeline on one dataset.

## Sources

- [cs.CL updates on arXiv.org](https://arxiv.org/abs/2610.31685)

---
Canonical: https://techandbusiness.org/newswire/Q1tnfMm-QSa6fo6C-MhYBm
Published: 2026-10-26T13:32:27.019Z
Story chronology: 2026-10-26T04:00:00.000Z
Retrieved: 2026-10-26T15:59:22.730Z
Publisher: Tech & Business (techandbusiness.org)