UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks

TL;DR

UpstreamQA introduces a modular framework that combines explicit upstream reasoning modules with large multimodal models to improve interpretability and performance in Video Question Answering tasks.

Contribution

The paper presents a novel modular framework that disentangles and evaluates core video reasoning components using explicit reasoning modules before downstream answering.

Findings

Explicit reasoning boosts VideoQA interpretability and performance.

Introducing reasoning modules can sometimes degrade performance at high baseline levels.

UpstreamQA enhances diagnostic transparency in multimodal video understanding.

Abstract

Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task's inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs) perform implicitly, leaving their internal decision process opaque. In contrast, large reasoning models (LRMs) explicitly generate intermediate logical steps that enhance interpretability and can improve multi-hop reasoning accuracy. Yet, these models are not designed for native video understanding, as they typically rely on static frame sampling. We propose UpstreamQA, a modular framework that disentangles and evaluates core video reasoning components through explicit upstream reasoning modules. Specifically, we employ multimodal LRMs to perform object identification and scene context generation before passing enriched reasoning traces to downstream LMMs for VideoQA. We evaluate UpstreamQA on the OpenEQA and NExTQA datasets using two LRMs (o4-mini, Gemini 2.5 Pro) and two LMMs (GPT-4o, Gemini 2.5 Flash). Our results demonstrate that introducing explicit reasoning can significantly boost performance and interpretability of downstream VideoQA, but can also lead to performance degradation when baseline performance is sufficiently high. Overall, UpstreamQA offers a principled framework for combining explicit reasoning and multimodal understanding, advancing both performance and diagnostic transparency in VideoQA in several scenarios.