Image de couverture de livre

Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Zhonghan, Ma, Ke, Chai, Wenhao, Wang, Xuan, Chen, Kewei, Guo, Dongxu, Zhang, Yanting, Wang, Hongwei, Wang, Gaoang
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft
par: Zhao, Zhonghan, et autres
Publié: (2024)

Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation
par: Zhao, Zhonghan, et autres
Publié: (2024)

See and Think: Embodied Agent in Virtual Environment
par: Zhao, Zhonghan, et autres
Publié: (2023)

Adaptive Graph Pruning for Multi-Agent Communication
par: Li, Boyi, et autres
Publié: (2025)

DynaHOI: Benchmarking Hand-Object Interaction for Dynamic Target
par: Hu, BoCheng, et autres
Publié: (2026)

User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning
par: Wang, Xuan, et autres
Publié: (2023)

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

QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?
par: Li, Yuanjun, et autres
Publié: (2025)

Do We Really Even Need Data?
par: Hoffman, Kentaro, et autres
Publié: (2024)

See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent
par: Tang, Tianci, et autres
Publié: (2026)

LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound
par: Guo, Xuechen, et autres
Publié: (2024)

EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments
par: Li, Dongping, et autres
Publié: (2025)

Do We Really Need a Large Number of Visual Prompts?
par: Kim, Youngeun, et autres
Publié: (2023)

Do We Really Need Immediate Resets? Rethinking Collision Handling for Efficient Robot Navigation
par: Wang, Shanze, et autres
Publié: (2026)

Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
par: Liu, Xiaoze, et autres
Publié: (2026)

Blind Inpainting with Object-aware Discrimination for Artificial Marker Removal
par: Guo, Xuechen, et autres
Publié: (2023)

Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?
par: Zhao, Zijian, et autres
Publié: (2025)

Ego3DT: Tracking Every 3D Object in Ego-centric Videos
par: Hao, Shengyu, et autres
Publié: (2024)

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
par: Wang, Zixu, et autres
Publié: (2026)

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
par: Jiao, Ruochen, et autres
Publié: (2024)

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
par: Wang, Yanbo, et autres
Publié: (2025)

Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
par: Wang, Jinze, et autres
Publié: (2025)

CityCraft: A Real Crafter for 3D City Generation
par: Deng, Jie, et autres
Publié: (2024)

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
par: Guo, Garvin, et autres
Publié: (2026)

Do We Really Need to Design New Byzantine-robust Aggregation Rules?
par: Fang, Minghong, et autres
Publié: (2025)

Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?
par: Malitesta, Daniele, et autres
Publié: (2024)

Pedagogy for Practical Library Instruction: What Do We "Really" Need to Know?
par: Montgomery, Molly
Publié: (2015)

Do We Really Need Cultural Diversity in the Library and Information Science Curriculum?
par: Welburn, William C.
Publié: (1994)

Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
par: Zhang, Hongming, et autres
Publié: (2024)

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
par: Qiu, Jiahao, et autres
Publié: (2025)

KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
par: Wang, Zixuan, et autres
Publié: (2024)

Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
par: Ito, Akira, et autres
Publié: (2025)

Do We Really Need End‐To‐End Continuous Processing for Biomanufacturing of Monoclonal Antibodies?
par: Anurag S. Rathore, et autres
Publié: (2025)

Do We Really Need Quantum Machine Learning?: A Multidimensional Empirical Study
par: Vhaduri, Sudip, et autres
Publié: (2026)

Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations
par: Zhou, Li, et autres
Publié: (2025)

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
par: Luo, Yinyi, et autres
Publié: (2026)

Do We Really Need Graph Convolution During Training? Light Post-Training Graph-ODE for Efficient Recommendation
par: Zhang, Weizhi, et autres
Publié: (2024)

Upgrade or Switch: Do We Need a Next-Gen Trusted Architecture for the Internet of AI Agents?
par: Raskar, Ramesh, et autres
Publié: (2025)

DNLSAT: A Dynamic Variable Ordering MCSAT Framework for Nonlinear Real Arithmetic
par: Wang, Zhonghan
Publié: (2024)

Improving NLSAT for Nonlinear Real Arithmetic
par: Wang, Zhonghan
Publié: (2024)