paper-with-me

홈 › Papers

PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments

2025-10-24 · Weijie Zhou, Xuantang Xiong, Yi Peng, Manli Tao, Chaoyang Zhao, Honghui Dong, Ming Tang, Jinqiao Wang arxiv

Visual reasoning in multimodal large language models (MLLMs) has primarily been studied in static, fully observable settings, limiting their effectiveness in real-world environments where information is often incomplete due to occlusion or limited field of view. Humans, in contrast, actively explore and interact with their environment-moving, examining, and manipulating objects-to gather information through a closed-loop process integrating perception, reasoning, and action. Inspired by this human capability, we introduce the Active Visual Reasoning (AVR) task, extending visual reasoning to partially observable, interactive environments. AVR necessitates agents to: (1) actively acquire information via sequential physical actions, (2) integrate observations across multiple steps for coherent reasoning, and (3) dynamically adjust decisions based on evolving visual feedback. To rigorously evaluate AVR, we introduce CLEVR-AVR, a simulation benchmark featuring multi-round interactive environments designed to assess both reasoning correctness and information-gathering efficiency. We present AVR-152k, a large-scale dataset that offers rich Chain-of-Thought (CoT) annotations detailing iterative reasoning for uncertainty identification, action-conditioned information gain prediction, and information-maximizing action selection, crucial for training agents in a higher-order Markov Decision Process. Building on this, we develop PhysVLM-AVR, an MLLM achieving state-of-the-art performance on CLEVR-AVR, embodied reasoning (OpenEQA, RoboVQA), and passive visual reasoning (GeoMath, Geometry30K). Our analysis also reveals that current embodied MLLMs, despite detecting information incompleteness, struggle to actively acquire and integrate new information through interaction, highlighting a fundamental gap in active reasoning capabilities.

📄 PDF Abstract BibTeX arXiv:2510.21111

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Reasoning

Similar Papers 제목 키워드 기반

PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability

2025-03-11 · CVPR 2025 1 · Weijie Zhou, Manli Tao, Chaoyang Zhao, Haiyun Guo 외

Understanding the environment and a robot's physical reachability is crucial for task execution. While state-of-the-art vision-language models (VLMs) excel in environmental perception, they often generate inaccurate or i…

Visual Reasoning

Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning

2026-06-13 · Zhengbo Zhang, Changtao Miao, Jinbo Su, Zhaowen Zhou 외 arxiv

Multimodal large language models (MLLMs) have demonstrated impressive capabilities in many visual tasks, but they often struggle with factual grounding when confronted with complex, open-world scenarios. While recent mul…

Visual Reasoning

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

2026-02-05 · Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao 외 arxiv

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely lang…

Reinforcement Learning

Interactive Sketchpad: A Multimodal Tutoring System for Collaborative, Visual Problem-Solving

2025-02-12 · Steven-Shine Chen, JiMin Lee, Paul Pu Liang

Humans have long relied on visual aids like sketches and diagrams to support reasoning and problem-solving. Visual tools, like auxiliary lines in geometry or graphs in calculus, are essential for understanding complex id…

Mathmultimodal interaction

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

2025-05-24 · Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee 외

We present v1, a lightweight extension to Multimodal Large Language Models (MLLMs) that enables selective visual revisitation during inference. While current MLLMs typically consume visual input only once and reason pure…

Mathematical ReasoningMultimodal ReasoningVisual Grounding