Copertina

Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Ying, Fang, Lihuang, Jiang, Rui, Wang, Mingxu, Gu, Zhifeng, Yi, Lei, Chen, Jie
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model
di: Xu, Wenjiang, et al.
Pubblicazione: (2025)

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
di: Chu, Zhaoyang, et al.
Pubblicazione: (2026)

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
di: Ju, Ruofei, et al.
Pubblicazione: (2026)

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
di: Cheng, Zihao, et al.
Pubblicazione: (2026)

Embodied AI Agents: Modeling the World
di: Fung, Pascale, et al.
Pubblicazione: (2025)

SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World
di: Zhang, Jiaqi, et al.
Pubblicazione: (2024)

Plan Verification for LLM-Based Embodied Task Completion Agents
di: Hariharan, Ananth, et al.
Pubblicazione: (2025)

HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied Theatrics
di: Jiang, Shufan, et al.
Pubblicazione: (2025)

SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents
di: Chen, Ruolin, et al.
Pubblicazione: (2025)

PhysiAgent: An Embodied Agent Framework in Physical World
di: Wang, Zhihao, et al.
Pubblicazione: (2025)

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
di: Chen, Hanyang, et al.
Pubblicazione: (2025)

"Are We Done Yet?": A Vision-Based Judge for Autonomous Task Completion of Computer Use Agents
di: Sumyk, Marta, et al.
Pubblicazione: (2025)

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
di: Gao, Chen, et al.
Pubblicazione: (2024)

MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
di: Xie, Zhengwei, et al.
Pubblicazione: (2026)

SIMA 2: A Generalist Embodied Agent for Virtual Worlds
di: SIMA team, et al.
Pubblicazione: (2025)

World Model Implanting for Test-time Adaptation of Embodied Agents
di: Yoo, Minjong, et al.
Pubblicazione: (2025)

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
di: Zhang, Qifan, et al.
Pubblicazione: (2026)

Batch Speculative Decoding Done Right
di: Zhang, Ranran Haoran, et al.
Pubblicazione: (2025)

Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
di: Jang, Jinwoo, et al.
Pubblicazione: (2026)

Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation
di: Bai, Qianqian, et al.
Pubblicazione: (2025)

HeteroHub: An Applicable Data Management Framework for Heterogeneous Multi-Embodied Agent System
di: Li, Xujia, et al.
Pubblicazione: (2026)

ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents
di: Wei, Bingqing, et al.
Pubblicazione: (2026)

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
di: Zhang, Hongxin, et al.
Pubblicazione: (2024)

SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
di: Kang, Haoqiang, et al.
Pubblicazione: (2026)

Embodied AI: From LLMs to World Models
di: Feng, Tongtong, et al.
Pubblicazione: (2025)

Learning Primitive Embodied World Models: Towards Scalable Robotic Learning
di: Sun, Qiao, et al.
Pubblicazione: (2025)

Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents
di: Zhang, Chunhui, et al.
Pubblicazione: (2026)

ASH: Agents that Self-Hone via Embodied Learning
di: Schneider, Benjamin, et al.
Pubblicazione: (2026)

EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots
di: Lei, Zixing, et al.
Pubblicazione: (2026)

Agentic AI-Empowered Conversational Embodied Intelligence Networks in 6G
di: Chen, Mingkai, et al.
Pubblicazione: (2025)

LoopTrap: Termination Poisoning Attacks on LLM Agents
di: Xu, Huiyu, et al.
Pubblicazione: (2026)

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation
di: Wang, Ning, et al.
Pubblicazione: (2025)

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
di: Lin, Minhua, et al.
Pubblicazione: (2026)

Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents
di: Bae, Seohui, et al.
Pubblicazione: (2025)

Are We Done with MMLU?
di: Gema, Aryo Pradipta, et al.
Pubblicazione: (2024)

OOWM: Structuring Embodied Reasoning and Planning via Object-Oriented Programmatic World Modeling
di: Chen, Hongyu, et al.
Pubblicazione: (2026)

FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation
di: Zou, Yuchen, et al.
Pubblicazione: (2026)

VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model
di: Wang, Zhizun, et al.
Pubblicazione: (2023)

See and Think: Embodied Agent in Virtual Environment
di: Zhao, Zhonghan, et al.
Pubblicazione: (2023)

Automatic Cognitive Task Generation for In-Situ Evaluation of Embodied Agents
di: He, Xinyi, et al.
Pubblicazione: (2026)