PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
PatchWorld:可执行世界模型的免梯度优化
Jiaxin Bai, Yue Guo, Yifei Dong, Jiaxuan Xiong, Tianshi Zheng, Yixia Li, Tianqing Fang, Yufei Li, Yisen Gao, Haoyu Huang, Zhongwei Xie, Hong Ting Tsang, Zihao Wang, Lihui Liu, Jeff Z. Pan, Yangqiu Song
机构
*
Hong Kong Baptist University(香港 Baptist 大学)
;
Independent Researcher(独立研究员)
;
HKUST(香港科技大学)
;
Beijing Institute of Technology(北京理工大学)
;
Southern University of Science and Technology(南方科技大学)
;
Wayne State University(韦恩州立大学)
;
University of Edinburgh(爱丁堡大学)
机构
*
East China Normal University(东华师范大学)
;
Shanghai Innovation Institute(上海创新研究院)
;
Shanghai Key Laboratory of Computer Software Evaluating and Testing(上海计算机软件评测与测试重点实验室)
;
Huawei Noah’s Ark Lab(华为诺亚实验室)
Comments18 pages, 1 figure, 6 tables. v4: PurgeBench is a companion benchmark by the same author (previously called "external"), plus a threats-to-validity note; no results changed. v3 added the memory-poison recovery evaluation and recover tool. Code: github.com/mthamil107/memorywire
机构
*
East China Normal University(华东师范大学)
;
Tongji University(同济大学)
;
Shanghai Jiao Tong University(上海交通大学)
;
Shanghai University of International Business and Economics(上海对外经贸大学)
;
Shenzhen Loop Area Institute(深圳河套学院)
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
SkillRevise: 通过轨迹条件技能修订改进LLM撰写的智能体技能
Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang, Qing Zong, Jiahe Guo, Zhongwei Xie, Yiyan Ji, Yauwai Yim, Hongyu Luo, Xiyu Ren, Ruan Chenyu, Haoran Li, Yangqiu Song
机构
*
The Hong Kong University of Science and Technology(香港科学与技术大学)
;
Harbin Institute of Technology(哈尔滨工业大学)
;
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳))
;
Nanjing University(南京大学)
;
The University of Hong Kong(香港大学)
UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale
RAISECity: 一种用于城市级现实对齐3D世界生成的多模态代理框架
Shengyuan Wang, Zhiheng Zheng, Yu Shang, Lixuan He, Yangcheng Yu, Fan Hangyu, Jie Feng, Qingmin Liao, Yong Li
机构
*
College of AI, Tsinghua University(人工智能学院,清华大学)
;
Shenzhen International Graduate School, Tsinghua University(深圳国际研究生院,清华大学)
;
Department of Electronic Engineering, BNRist, Tsinghua University(电子工程系,北京研究院,清华大学)
Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents (Extended Revision: From Behavioral Architecture to Epistemic Accountability)
CommentsThis revised version extends the original SCL framework from a behavioral architecture for reliable LLM agents into a broader architecture of epistemic accountability, integrating context-aware Human-in-the-Loop control, Pool-Gated Retrieval, and the Horizon-Warrant-Commitment structure