StreamReady: Learning *What* to Answer and *When* in Long Streaming Videos

Shehreen Azad, Vibhav Vineet, Yogesh S Rawat

Keywords: multimodal reasoning, answer- readiness, streaming video understanding

TL;DR: We introduce readiness-aware streaming video understanding with StreamReady framework, ProReady-QA Benchmark and Answer Readiness Score (ARS) evaluation metric.

Abstract: Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence reflects speculation, answering after it has passed reduces real-time utility. To capture this behavior, we introduce a readiness-aware formulation of streaming video understanding with the **Answer Readiness Score (ARS)**, a timing-aware objective with asymmetric early and late penalties. When combined with correctness, ARS defines an effective accuracy that measures not just whether a model is right, but whether it answers at the appropriate moment. Building on this formulation, we introduce **StreamReady**, a framework to unify temporal reasoning with on-time answering through a lightweight readiness mechanism that decides if sufficient evidence has been observed before responding. To evaluate this capability, we further introduce ProReady-QA, a benchmark with annotated answer evidence windows and proactive multi-turn questions across local and global contexts. StreamReady achieves superior performance on **ProReady-QA**, and consistently outperforms prior methods across eight additional streaming and offline long-video benchmarks, demonstrating robust and broadly generalizable video understanding capability.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 6