Image de couverture de livre

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Garvin, Yu, Donglei, Chen, Yu, Wang, Xiang, Li, Shuai, Zhao, Xinpei, Liu, Huaxing, Wang, Qinghao, Liao, Minpeng
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
par: Guo, Garvin, et autres
Publié: (2026)

Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model
par: Zhao, Zhonghan, et autres
Publié: (2024)

MambaOut: Do We Really Need Mamba for Vision?
par: Yu, Weihao, et autres
Publié: (2024)

VFaith: Do Large Multimodal Models Really Reason on Seen Images Rather than Previous Memories?
par: Yu, Jiachen, et autres
Publié: (2025)

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
par: Tian, Changyuan, et autres
Publié: (2026)

Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
par: Ou, Siqu, et autres
Publié: (2026)

Do Pre-trained Models Benefit Equally in Continual Learning?
par: Lee, Kuan-Ying, et autres
Publié: (2022)

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
par: Fan, Yingqi, et autres
Publié: (2026)

Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?
par: Lyu, Yunbo, et autres
Publié: (2025)

Evaluating the Visual Similarity of Southwest China's Ethnic Minority Brocade Based on Deep Learning
par: Liu, Shichen, et autres
Publié: (2024)

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning
par: Ashraf, Tajamul, et autres
Publié: (2025)

What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
par: Ma, Yan, et autres
Publié: (2026)

TempCompass: Do Video LLMs Really Understand Videos?
par: Liu, Yuanxin, et autres
Publié: (2024)

Cooperative Sentiment Agents for Multimodal Sentiment Analysis
par: Wang, Shanmin, et autres
Publié: (2024)

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
par: Shiri, Fatemeh, et autres
Publié: (2024)

MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning
par: Wang, Chenyu, et autres
Publié: (2024)

A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis
par: Li, Yingshu, et autres
Publié: (2023)

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
par: Chen, Zhaorun, et autres
Publié: (2024)

Imp: Highly Capable Large Multimodal Models for Mobile Devices
par: Shao, Zhenwei, et autres
Publié: (2024)

DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Models
par: Wang, Jiarui, et autres
Publié: (2025)

OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
par: Jia, Hongrui, et autres
Publié: (2025)

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture
par: Fu, Biao, et autres
Publié: (2025)

ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
par: Ding, Shengyuan, et autres
Publié: (2025)

CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains
par: Wang, Wenhan, et autres
Publié: (2026)

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
par: Yu, Weihao, et autres
Publié: (2023)

Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
par: Qin, Tian, et autres
Publié: (2026)

RAISECity: A Multimodal Agent Framework for Reality-Aligned 3D World Generation at City-Scale
par: Wang, Shengyuan, et autres
Publié: (2025)

Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
par: Wei, Qianshan, et autres
Publié: (2026)

AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture
par: Ye, Zi, et autres
Publié: (2026)

Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
par: Tan, Cheng, et autres
Publié: (2024)

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory
par: Xiao, Yunzhong, et autres
Publié: (2025)

LLaVA-Critic: Learning to Evaluate Multimodal Models
par: Xiong, Tianyi, et autres
Publié: (2024)

KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?
par: Wang, Xianfeng, et autres
Publié: (2026)

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent
par: Liao, Xinyao, et autres
Publié: (2025)

Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
par: Yan, Shilin, et autres
Publié: (2026)

Do Vision-Language Models Really Understand Visual Language?
par: Hou, Yifan, et autres
Publié: (2024)

Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
par: Das, Anudeep, et autres
Publié: (2025)

Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
par: Lv, Shuai, et autres
Publié: (2026)

Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?
par: Sun, Ruiqing, et autres
Publié: (2026)

What Really Matters for Robust Multi-Sensor HD Map Construction?
par: Hao, Xiaoshuai, et autres
Publié: (2025)