---
id: 20260508-T0-13
title: "Pro$^2$Assist：通过多模态感知实现长程任务主动辅助"
title_en: "Pro$^2$Assist Enables Proactive Assistance for Long Tasks"
url: https://ai.daily.yangsir.net/daily/20260508-T0-13
issue_date: 2026-05-08
publish_date: 2026-05-07T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2605.04227
---

# Pro$^2$Assist：通过多模态感知实现长程任务主动辅助

卡内基梅隆大学研究团队发布Pro$^2$Assist模型，通过多模态感知主动预测用户下一步操作。该系统可识别8类日常任务中的连续步骤，如烹饪或组装，准确率比现有方案提高23%。研究显示，主动辅助能减少用户37%的重复操作时间，适用于智能家居和远程协作场景。论文已在arXiv发布，代码开源。

## English Version

**Pro$^2$Assist Enables Proactive Assistance for Long Tasks**

Carnegie Mellon researchers released Pro$^2$Assist, a model that proactively predicts user actions for long-horizon tasks using multimodal perception. It handles 8+ daily activities (cooking, assembly) with 23% higher accuracy than prior systems. The approach reduces repetitive operations by 37%, with applications in smart homes and remote assistance. Code is open-sourced on arXiv.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2605.04227)

**详情页**：https://ai.daily.yangsir.net/daily/20260508-T0-13

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*