Cradle: Empowering Foundation Agents towards General Computer Control
Weihao Tan, Wentao Zhang, Xinrun Xu, Haochong Xia, Ziluo Ding, Boyu Li, Bohan Zhou, Junpeng Yue, Jiechuan Jiang, Yewen Li, Ruyi An, Molei Qin
摘要
agents.github.io/Cradle Everyday I n f o r m a t i o n G a t h e r i n g A c t i o n P l a n n i n g T a s k I n f e r e n c e S k i l l C u r a t i o n S e l f -R e f l e c t i o n R e t r i e v e d S k i l l s : [' a i m ' ,' f o l l o w ' ,' t u r n ' ,' m o v e _ f o r w a r d ' ,'s h o w _ w e a p o n _ w h e e l ' . . . ]L a s t A c t i o n : t a k e _ c o v e r ( ) P r e v i o u s T a s k : P r e s s [ Q ] t o t a k e c o v e r . T h e l a s t a c t i o n w a s e x e c u t e d s u c c e s s f u l l y , a n d t h e t a s k i s c o m p l e t e d s i n c e n e w g u i d a n c e a p p e a r s . H o l d [ T A B ] t o s h o w t h e W e a p o n W h e e l . s h o w _ w e a p o n _ w h e e l ( ) H o l d [ T A B ] t o s h o w t h e W e a p o n W h e e l . G e n e r a t e d S k i l l : d e f s h o w _ w e a p o n _ w h e e l ( ) : i o _ e n v . k e y _ h o l d (' t a b ' )G u i d a n c e : # S e l e c t s p a r s n i p s e e d s f r o m t h e t o o l b a r . s e l e c t _ t o o l (k e y =' 6 ' ) # P l a n t s p a r s n i p s e e d s o n t h e t i l l e d s o i l . d o _ a c t i o n ( ) R e t r i e v e d S k i l l s : [' m o v e _ u p ' ,' m o v e _ d o w n ' ,' m o v e _ l e f t ' ,' m o v e _ r i g h t ' ,' s e l e c t _ t o o l ' ,' d o _ a c t i o n ' . .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper30
- Group-in-Group Policy Optimization for LLM Agent TrainingLang Feng, Zhenghai Xue, Tingcong Liu, Bo AnNeurIPS 2025 · 被引用 484 次
- lmgame-Bench: How Good are LLMs at Playing Games?Lanxiang Hu, Mingjia Huo, Yuxuan Zhang, Haoyang Yu 等ICLR 2026 · 被引用 47 次
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic TasksShuo He, Lang Feng, Qi Wei, Xin Cheng 等ICLR 2026 · 被引用 36 次
- Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video GamesDongmin Park, Minkyu Kim, Beongjun Choi, Junhyuck Kim 等ICLR 2026 · 被引用 30 次
- NitroGen: An Open Foundation Model for Generalist Gaming AgentsLoïc Magne, Anas Awadalla, Guanzhi Wang, Yinzhen Xu 等CVPR 2026 · 被引用 22 次
它引用的顶会 Paper23
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 被引用 13,211 次
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan 等NeurIPS 2023 · 被引用 5,828 次
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran 等NeurIPS 2023 · 被引用 5,068 次
- PaLM-E: An Embodied Multimodal Language ModelDanny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch 等ICML 2023 · 被引用 2,601 次
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris 等UIST 2023 · 被引用 1,882 次
相关 Paper
- Towards Unobtrusive Physical AI: Augmenting Everyday Objects with Intelligence and Robotic Movement for Proactive AssistanceViolet Yinuo Han, Jesse T. Gonzalez, Christina Yang, Zhiruo Wang 等UIST 2025 · 被引用 3 次
- MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference LearningHuang Kun, Weikai Xu, Yuxuan Liu, Quandong Wang 等ICLR 2026 · 被引用 9 次
- CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation ModelZhuoyuan Yu, Yuxing Long, Zihan Yang, Chengyan Zeng 等AAAI 2026 · 被引用 14 次
- Action-Sketcher: From Reasoning to Action via Visual Sketches for Robotic ManipulationHuajie Tan, Peterson Co, Yijie Xu, Shanyu Rong 等CVPR 2026
- Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement LearningYulei Qin, Xiaoyu Tan, Zhengbao He, Gang Li 等ICLR 2026 · 被引用 9 次
