REVISOR：超越文本反思，邁向長影片理解中的多模態內省推理

REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding

November 17, 2025

作者: Jiaze Li, Hao Yin, Wenhui Tan, Jingyang Chen, Boshen Xu, Yuxun Qu, Yijing Chen, Jianzhong Ju, Zhenbo Luo, Jian Luan

cs.AI

摘要

依賴純文字反思機制的自我反思方法在多數多模態任務中表現良好，但直接應用於長影片理解場景時會顯現明顯侷限性。其根本原因在於兩點：(1)長影片理解涉及更豐富且動態的視覺輸入，僅對文字信息進行反思不足夠，必須針對視覺信息建立專門的反思流程；(2)純文字反思機制缺乏跨模態互動能力，無法在反思過程中充分整合視覺信息。基於這些發現，我們提出REVISOR（面向反思的視覺片段定向推理框架），這是一種新型工具增強型多模態反思架構。REVISOR使多模態大語言模型能夠協同構建跨文本與視覺模態的內省式反思流程，顯著增強其長影片推理能力。為確保REVISOR在強化學習中能精準審閱與問題高度相關的影片片段，我們設計了雙重歸因解耦獎勵機制（DADR）。該機制整合於GRPO訓練策略中，能強化模型推理與所選影片證據間的因果對齊。值得注意的是，REVISOR框架無需額外的監督微調或外部模型，即可顯著提升多模態大語言模型的長影片理解能力，在VideoMME、LongVideoBench、MLVU和LVBench四個基準測試中均取得優異成果。

English

Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental reasons for this lie in two points: (1)long-form video understanding involves richer and more dynamic visual input, meaning rethinking only the text information is insufficient and necessitates a further rethinking process specifically targeting visual information; (2) purely text-based reflection mechanisms lack cross-modal interaction capabilities, preventing them from fully integrating visual information during reflection. Motivated by these insights, we propose REVISOR (REflective VIsual Segment Oriented Reasoning), a novel framework for tool-augmented multimodal reflection. REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding. To ensure that REVISOR can learn to accurately review video segments highly relevant to the question during reinforcement learning, we designed the Dual Attribution Decoupled Reward (DADR) mechanism. Integrated into the GRPO training strategy, this mechanism enforces causal alignment between the model's reasoning and the selected video evidence. Notably, the REVISOR framework significantly enhances long-form video understanding capability of MLLMs without requiring supplementary supervised fine-tuning or external models, achieving impressive results on four benchmarks including VideoMME, LongVideoBench, MLVU, and LVBench.