arXiv 2603.173122026-03-18cs.CVcs.AI

基于视觉语言模型的递归推理用于估计长周期具身任务进度

Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress

Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院）；Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理研究重点实验室）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（教育部下一代智能搜索与推荐工程研究中心）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）

Yuelin Zhang, Sijie Cheng, Chen Li, Zongzhao Li, Yuxin Huang, Yang Liu, Wenbing Huang

备注：: CVPR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出R²VLM模型，通过递归推理框架处理局部视频片段，维护全局上下文，实现复杂时间依赖推理，提升长周期任务进度估计性能。

摘要：

准确估计任务进度对具身智能体执行长周期、多步骤任务至关重要。尽管已有进展，现有基于视觉语言模型（VLMs）的方法主要利用视频理解能力，忽视其复杂推理潜力。此外，使用VLMs处理长视频轨迹在现实部署中计算成本过高。为解决这些问题，我们提出递归推理视觉语言模型（R²VLM）。该模型具有递归推理框架，通过迭代处理局部视频片段，通过演进的思维链（CoT）维护全局上下文。此CoT显式记录任务分解、关键步骤及其完成状态，使模型能够推理复杂的时间依赖性。此设计避免了处理长视频的高成本，同时保留了必要的推理能力。我们在大规模自动生成的ALFRED和Ego4D数据集上训练R²VLM。在进度估计和下游应用（包括进度增强的策略学习、强化学习奖励建模和主动协助）的广泛实验中，R²VLM表现出强大的性能和泛化能力，在长周期任务进度估计中达到新的最先进的水平。模型和基准已公开在https://huggingface.co/collections/zhangyuelin/r2vlm。

英文摘要：

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video understanding capabilities, while neglecting their complex reasoning potential. Furthermore, processing long video trajectories with VLMs is computationally prohibitive for real-world deployment. To address these challenges, we propose the Recurrent Reasoning Vision-Language Model ($\text{R}^2$VLM). Our model features a recurrent reasoning framework that processes local video snippets iteratively, maintaining a global context through an evolving Chain of Thought (CoT). This CoT explicitly records task decomposition, key steps, and their completion status, enabling the model to reason about complex temporal dependencies. This design avoids the high cost of processing long videos while preserving essential reasoning capabilities. We train $\text{R}^2$VLM on large-scale, automatically generated datasets from ALFRED and Ego4D. Extensive experiments on progress estimation and downstream applications, including progress-enhanced policy learning, reward modeling for reinforcement learning, and proactive assistance, demonstrate that $\text{R}^2$VLM achieves strong performance and generalization, achieving a new state-of-the-art in long-horizon task progress estimation. The models and benchmarks are publicly available at \href{https://huggingface.co/collections/zhangyuelin/r2vlm}{huggingface}.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。