UniT：統一多模態思維鏈測試時縮放

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

February 12, 2026

作者: Leon Liangyu Chen, Haoyu Ma, Zhipeng Fan, Ziqi Huang, Animesh Sinha, Xiaoliang Dai, Jialiang Wang, Zecheng He, Jianwei Yang, Chunyuan Li, Junzhe Sun, Chu Wang, Serena Yeung-Levy, Felix Juefei-Xu

cs.AI

摘要

統一模型能夠在單一架構中處理多模態理解與生成任務，但其通常以單次前向運作方式執行，缺乏對輸出結果的迭代優化。許多多模態任務（特別是涉及複雜空間構圖、多個互動物件或動態指令的場景）需要分解指令、驗證中間結果並進行迭代修正。雖然測試時擴展技術已證明通過分配額外推理計算資源進行迭代推理能顯著提升語言模型性能，但將此範式擴展至統一多模態模型仍是待解決的挑戰。我們提出UniT框架，透過多模態思維鏈測試時擴展，使單一統一模型能進行多輪推理、驗證與優化。UniT融合智能體數據合成、統一模型訓練與靈活的測試時推理機制，激發出包含驗證、子目標分解與內容記憶等認知行為。我們的核心發現包括：（1）基於短推理軌跡訓練的統一模型，在測試時能泛化至更長的推理鏈；（2）序列式思維鏈推理相比並行採樣，提供了更具可擴展性與計算效率的測試時擴展策略；（3）結合生成與編輯軌跡的訓練能提升模型在分佈外視覺推理任務的表現。這些成果確立了多模態測試時擴展作為推進統一模型生成與理解能力的有效範式。

English

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving complex spatial compositions, multiple interacting objects, or evolving instructions, require decomposing instructions, verifying intermediate results, and making iterative corrections. While test-time scaling (TTS) has demonstrated that allocating additional inference compute for iterative reasoning substantially improves language model performance, extending this paradigm to unified multimodal models remains an open challenge. We introduce UniT, a framework for multimodal chain-of-thought test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds. UniT combines agentic data synthesis, unified model training, and flexible test-time inference to elicit cognitive behaviors including verification, subgoal decomposition, and content memory. Our key findings are: (1) unified models trained on short reasoning trajectories generalize to longer inference chains at test time; (2) sequential chain-of-thought reasoning provides a more scalable and compute-efficient TTS strategy than parallel sampling; (3) training on generation and editing trajectories improves out-of-distribution visual reasoning. These results establish multimodal test-time scaling as an effective paradigm for advancing both generation and understanding in unified models.