---
format: "aidr-story-markdown/v1"
id: "827c370c6c8dc1f6a09ccef3dbca0b5860e70804ceb4d1f3757290c6623d3dd8"
canonical_url: "https://aidr.today/827c370c?lang=en"
title: "StreamVibe: Proactive Video Agents for Evolving User Intent"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-27T00:00:00.000Z"
category: "Research"
topics: ["agent"]
source_urls: ["https://huggingface.co/papers/2610.34662"]
summary: "StreamVibe introduces a benchmark and model for proactive video agents that infer implicit user intents from continuous observations and dynamically update interactions as intents evolve. The approach includes StreamVibe-Bench with 4.1K evaluation and 85K training samples, StreamVibe-VL as a streaming proactive model, and StreamVibe-Harness for maintaining user intents as persistent states via hierarchical memory."
---

# StreamVibe: Proactive Video Agents for Evolving User Intent

> [Open the canonical story](<https://aidr.today/827c370c?lang=en>)

**Published:** 2026-10-27T00:00:00.000Z
**Category:** Research
**Topics:** agent

## Summary

StreamVibe introduces a benchmark and model for proactive video agents that infer implicit user intents from continuous observations and dynamically update interactions as intents evolve\. The approach includes StreamVibe\-Bench with 4\.1K evaluation and 85K training samples, StreamVibe\-VL as a streaming proactive model, and StreamVibe\-Harness for maintaining user intents as persistent states via hierarchical memory\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.34662>)