---
format: "aidr-story-markdown/v1"
id: "e01efa46cf6e0694d9982798b4687a9e8c1e8c55113a3bbedb5712e128ea24c3"
canonical_url: "https://aidr.today/e01efa46?lang=en"
title: "Turns Matter: Advancing Streaming Video RL via Turn-Level Credit"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-05T00:00:00.000Z"
category: "Research"
topics: ["agent"]
source_urls: ["https://huggingface.co/papers/2611.06728"]
summary: "TurnWise is a turn-level Group Relative Policy Optimization framework for streaming video that assigns credit to individual decisions using silence-completed prefix scoring and turn-mean policy optimization to reduce redundancy and improve response quality."
---

# Turns Matter: Advancing Streaming Video RL via Turn\-Level Credit

> [Open the canonical story](<https://aidr.today/e01efa46?lang=en>)

**Published:** 2026-11-05T00:00:00.000Z
**Category:** Research
**Topics:** agent

## Summary

TurnWise is a turn\-level Group Relative Policy Optimization framework for streaming video that assigns credit to individual decisions using silence\-completed prefix scoring and turn\-mean policy optimization to reduce redundancy and improve response quality\.

## Sources

- [Story source](<https://huggingface.co/papers/2611.06728>)