AI Agent

Factorised Active Inference for Strategic Multi-Agent Interactions

Jaime Ruiz-Serra, Patrick Sweeney, Michael S. Harré

机构 * Centre for Complex Systems, The University of Sydney（复杂系统中心，悉尼大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.LG

Comments To appear in Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2025). Detroit, USA, May 2025

Decentralized Multi-agent Plan Repair in Dynamic Environments

Antonín Komenda, Peter Novák, Michal Pěchouček

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.AI

Comments 21 pages, 5 algorithms, 3 figures. This is the full version of an extended abstract published in Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), Conitzer, Winikoff, Padgham, and van der Hoek (eds.), June, 4--8, 2012, Valencia, Spain

Kimi K2.5: Visual Agentic Intelligence

Kimi K2.5：视觉代理智能

Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S. H. Cai, Yuan Cao, Ziwei Chai, Y. Charles, H. S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Yean Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Hao Ding, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Angang Du, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yu Fan, Shengjun Fang, Qiulin Feng, Yichen Feng, Garimugai Fu, Kelin Fu, Hongcheng Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Qizheng Gu, Xinran Gu, Yicheng Gu, Longyu Guan, Shuhao Guan, Yuanying Guo, Xiaoru Hao, Dailan He, Tianhong He, Weiran He, Wenyang He, Yibo He, Yunjia He, Chao Hong, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Chaobo Jia, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guokun Lai, Aidi Li, C. Li, Cheng Li, Fang Li, Guanghe Li, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li, Yuxiao Li, Zhaowei Li, Zhaoxi Li, Zheming Li, Weilong Liao, Jiawei Lin, Xiaohan Lin, Yibo Lin, Zhishan Lin, Zichao Lin, Cheng Liu, Chenyu Liu, Hongzhang Liu, Liang Liu, Shaowei Liu, Shudong Liu, Shuran Liu, Tianwei Liu, Tianyu Liu, Weizhou Liu, Xiangyan Liu, Yangyang Liu, Yanming Liu, Yibo Liu, Yuanxin Liu, Zhengying Liu, Zhongnuo Liu, Enzhe Lu, Haoyu Lu, Zhiyuan Lu, G. Luo, Junyu Luo, Tongxu Luo, Yashuo Luo, Long Ma, Shaoguang Mao, Yuan Mei, Xin Men, Fanqing Meng, Zhiyong Meng, Yibo Miao, Minqing Ni, Kun Ouyang, Siyuan Pan, Bo Pang, Yuchao Qian, Ruoyu Qin, Zeyu Qin, Jiezhong Qiu, Bowen Qu, Zeyu Shang, Youbo Shao, Tianxiao Shen, Zhennan Shen, Juanfeng Shi, Lidong Shi, Shengyuan Shi, Feifan Song, Pengwei Song, Tianhui Song, Xiaoxi Song, Hongjin Su, Jianlin Su, Zhaochen Su, Lin Sui, Jinsong Sun, Junyao Sun, Tongyu Sun, Flood Sung, Yunpeng Tai, Chuning Tang, Heyi Tang, Xiaojuan Tang, Zhengyang Tang, Jiawen Tao, Shiyuan Teng, Chaoran Tian, Pengfei Tian, Bowen Wang, Chensi Wang, Chuang Wang, Congcong Wang, Dingkun Wang, Dinglu Wang, Dongliang Wang, Feng Wang, Hailong Wang, Haiming Wang, Hao Wang, Hengzhi Wang, Huaqing Wang, Hui Wang, Jiahao Wang, Jinhong Wang, Jiuzheng Wang, Kaixin Wang, Linian Wang, Qibin Wang, Shengjie Wang, Shuyi Wang, Si Wang, Wei Wang, Xiaochen Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yipu Wang, Yiqin Wang, Yucheng Wang, Yuzhi Wang, Zhaoji Wang, Zhaowei Wang, Zhengtao Wang, Zhexu Wang, Zifan Wang, Zihan Wang, Zizhe Wang, Chu Wei, Ming Wei, Chuan Wen, Zichen Wen, Chengjie Wu, Haoning Wu, Junyan Wu, Rucong Wu, Wenhao Wu, Yuefeng Wu, Yuhao Wu, Yuxin Wu, Zijian Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Yuchong Xie, Bowei Xing, Boyu Xu, Jianfan Xu, Jing Xu, Jinjing Xu, L. H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinbo Xu, Xinran Xu, Yangchuan Xu, Yichang Xu, Yuemeng Xu, Zelai Xu, Ziyao Xu, Junjie Yan, Yuzi Yan, Guangyao Yang, Hao Yang, Junwei Yang, Kai Yang, Ningyuan Yang, Xiaofei Yang, Xinlong Yang, Xinyu Yang, Ying Yang, Yi Yang, Yi Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Dan Ye, Haoran Ye, Wenjie Ye, Zhuorui Ye, Peng Yebo, Bohong Yin, Chengzhen Yu, Longhui Yu, Tao Yu, Tianxiang Yu, Enming Yuan, Mengjie Yuan, Xiaokun Yuan, Yang Yue, Weihao Zeng, Dunyuan Zha, Haobing Zhan, Dehao Zhang, Hao Zhang, Jin Zhang, Puqi Zhang, Qiao Zhang, Rui Zhang, Xiaobin Zhang, Xiaoyun Zhang, Y. Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yushun Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Chenguang Zhao, Feifan Zhao, Jinxiang Zhao, Shuai Zhao, Xiangyu Zhao, Xuanle Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Ruihan Zheng, Shaojie Zheng, Tengyang Zheng, Junfeng Zhong, Longguang Zhong, Weiming Zhong, M. Zhou, Runjie Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Liya Zhu, Xinhao Zhu, Yuxuan Zhu, Zhen Zhu, Jingze Zhuang, Weiyu Zhuang, Ying Zou, Xinxing Zu

机构 * Kimi Team（Kimi 团队） 纠错

专题命中 多智能体 ：agent(summary_cn,abstract)；agentic(title,abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结 Kimi K2.5通过联合优化文本和视觉模态，提出Agent Swarm框架，实现多模态代理智能的先进性能和高效任务处理。

Comments Kimi K2.5 tech report

Auditing Emergent LLM-Agent Collaboration through Cooperation-Obligation Coupling

通过合作-义务耦合对大语言模型智能体（LLM-agent）的涌现协作进行审计

Zuyuan Zhang, Hanqing Yang, Carlee Joe-Wong, Tian Lan

专题命中 多智能体 ：agent(title,title_cn)

AI总结 针对LLM-agent协作审计的可审计性缺口，本文提出iCORE表示方法，建立合作-义务耦合审计框架，实验验证其可准确检测缺陷并显著提升轨迹与终端性能。

Agent-OSI: An Interoperability Architecture for Communication and Settlement in the Decentralized Internet of Agents

Agent-OSI: 向去中心化的智能体互联网的分层协议栈

Wenxin Xu, Taotao Wang, Yihan Xia, Shengli Zhang, Soung Chang Liew

专题命中 多智能体 ：agent(title,title_cn)

AI总结 Agent-OSI提出了一种基于现有互联网的六层协议栈，旨在实现去中心化智能体网络的互操作性、信任和按使用付费结算。

Comments 8 pages, 3 figures

Multi-Agent Robotic Control with Onboard Vision-Language Models

基于机载视觉语言模型的多智能体机器人控制

Kajetan Rachwał, Maciej Majek, Bartłomiej Boczek, Jakub Matejczyk, Dominik Matejkowski, Adam Dąbrowski, Tim Seyde, Alexander Amini, Maria Ganzha

机构 * Faculty of Mathematics and Information Science, Warsaw University of Technology（华沙技术大学数学与信息科学学院） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

AI总结 研究针对视觉语言模型用于机器人控制的挑战，提出多智能体系统架构，在机载硬件部署智能体，用紧凑型VLMs并经微调及新型编排智能体，经硬件在环模拟验证，证明该机载架构可行高效，有实际应用潜力且模拟环境已开源。

Comments 6 pages, 2 figures, accepted to 24th International Conference on Practical applications of Agents and Multi-Agent Systems (PAAMS'26)

Envisioning Sensemaking in Multi-Human, Multi-Agent Collaborative Knowledge Work

设想多人类、多智能体协作知识工作中的意义建构

Zhitong Guan, Soo Young Rieh

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；AI agent(abstract)

AI总结 探讨生成式AI如何重塑协作知识工作中的意义建构，提出五项设计原则及一个动态共享表征工作空间框架，支持人类与AI代理共同构建可协商的知识。

Comments This is the Author's Accepted Manuscript version of the article: Guan, Z., \& Rieh, S. Y. (2026). Envisioning Sensemaking in Multi-Human, Multi-Agent Collaborative Knowledge Work. Accepted for publication in \textit{Sensemaking @ CHI 2026}

MAEBE: Multi-Agent Emergent Behavior Framework

Sinem Erisken, Timothy Gothard, Martin Leitgab, Ram Potham

机构 * Independent Researcher（独立研究者） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments Preprint. This work has been submitted to the Multi-Agent Systems Workshop at ICML 2025 for review

Asynchronous Spatial-Temporal Allocation for Trajectory Planning of Heterogeneous Multi-Agent Systems

Yuda Chen, Haoze Dong, Zhongkui Li

专题命中 多智能体 ：agent(title,abstract)；planning(title)；multi-agent(title)

Comments 8 pages

Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering

Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments A full version of the paper will be released soon. The codes are available at https://github.com/bowen-upenn/Multi-Agent-VQA

Pommerman: A Multi-Agent Playground

Cinjon Resnick, Wes Eldridge, David Ha, Denny Britz, Jakob Foerster, Julian Togelius, Kyunghyun Cho, Joan Bruna

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments Oral at the AIIDE Multi-Agent Workshop; 0xc8Ac61A4025B35e425b829fCFCab37f038993963

Modeling Communication of Collaborative Multi-Agent System under Epistemic Planning

Abeer Alshehri, Tim Miller, Liz Sonenberg

专题命中 多智能体 ：planning(title,abstract)；agent(title)；multi-agent(title)

Comments 19 pages, 6 figures, 4 tables Submitted to International Journal of Intelligent Systems

Journal ref Int J Intell Syst. 2021; 1- 22

Re-conceptualising the Language Game Paradigm in the Framework of Multi-Agent Reinforcement Learning

Paul Van Eecke, Katrien Beuls

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL、cs.LG

Comments This paper was accepted for presentation at the 2020 AAAI Spring Symposium `Challenges and Opportunities for Multi-Agent Reinforcement Learning' after a double-blind reviewing process

Multi-Agent System Interaction in Integrated SCM

Ritu Sindhu, Abdul Wahid, G. N. Purohit

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments International Journal of Computer Science Issues, IJCSI Volume 5, pp33-37, October 2009

Journal ref R. Sindhu, A. W. and G.N.Purohit, "Multi-Agent System Interaction in Integrated SCM", International Journal of Computer Science Issues, IJCSI, Volume 5, pp33-37, October 2009

Towards Participatory Design of Multi-agent Approach to Transport Demands

Yee Ming Chen, Bo-Yuan Wang

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)

Comments "International Journal of Computer Science Issues, IJCSI, Volume 4, Issue 1, pp10-15, September 2009"

Journal ref Y. M. Chen and B. Wang, "Towards Participatory Design of Multi-agent Approach to Transport Demands ", International Journal of Computer Science Issues, IJCSI, Volume 4, Issue 1, pp10-15, September 2009

The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration

对话的几何学：基于图谱的语言模型揭示多智能体协作的协同团队

Kotaro Furuya, Yuichi Kitagawa

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.CL；agentic(comments)

AI总结 本文提出一种基于交互的自动团队组建框架，通过构建语言模型图谱揭示多智能体协作的协同团队，实验表明其能发现功能一致的团队并优于随机基线。

Comments Accepted at the AAAI-26 Workshop on LLM-based Multi-Agent Systems: Towards Responsible, Reliable, and Scalable Agentic Systems (LaMAS 2026) as an oral presentation

Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning

Claude Formanek, Asad Jeewa, Jonathan Shock, Arnu Pretorius

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.LG；autonomous agent(comments)

Comments Extended Abstract at Autonomous Agents and Multi-Agent Systems Conference 2023

Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research

一次对账，随时撰写：用于无漂移、时点研究的信任分层图书馆与多智能体撰写器

Xing Zhang, Yanwei Cui, Guanghui Wang, Peiyang He

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.CL

AI总结 该研究提出双层智能体系统，通过信任分层图书馆与多智能体撰写器分离知识库与报告撰写，消除报告矛盾与漂移，实验验证其在多指标、多场景下的有效性与效率优势。

NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation

NeuroRefiner：面向3D荧光显微镜神经元分割的形态感知多智能体细化方法

Haiyang Yan, Jinyue Guo, Yanchao Zhang, Bingqing Wang, Zhenchen Li, Jing Liu, Jiazheng Liu, Linlin Li, Hua Han

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； Beijing Normal University（北京师范大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；workflow(abstract)；分类 cs.AI

AI总结 针对3D荧光显微镜神经元分割的拓扑与细节保留难题，本文提出NeuroRefiner多智能体系统结合TopoRefineNet工具，在多数据集上实现优于现有方法的分割性能，ZBFWB数据集F1分数提升3.02%。

Comments Accept by ECCV 2026

IDRAAK: From Multi-Agent NLP to Few-Shot Prompting for Semantic Drift Detection in Technical Requirements

IDRAAK：从多智能体自然语言处理到用于技术需求语义漂移检测的少样本提示

Shiva Ahir

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.CL

AI总结 IDRAAK是基于语义需求表示的可解释框架，通过含6个少样本示例的LLM单次调用检测技术需求语义漂移，性能优于多种替代方案，证明少样本提示是高效替代方法。

Stateful Multi-Agent LLMs for Cross-View Interface Alignment in Automotive Model-Based Systems Engineering

面向汽车基于模型的系统工程的有状态多智能体大语言模型，用于跨视图接口对齐

Aleksei Velsh, Nenad Petrovic, Alois Knoll

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；workflow(abstract)；分类 cs.SE

AI总结 针对LLMs在汽车MBSE中引发的架构漂移问题，提出有状态多智能体验证流水线，在ADAS场景中实现97%实体可追溯性等指标，证明对抗性审核可让LLMs可靠生成零错误MBSE架构。

Multi-agent discovery of practical quantum LDPC codes

多智能体发现实用量子低密度奇偶校验码

Dongheng Qian, Tianyi Li

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 该研究开发多智能体框架，在块长不超过400、总重量不超过10的二元CSS码范围内，发现了多种高性能实用量子LDPC码，为实验评估提供了硬件相关候选。

Comments 20 pages, 3 figures

A Multi-Agent Framework for Automated Coarse-Grained Molecular Dynamics of Polymers

用于聚合物自动化粗粒度分子动力学的多智能体框架

Joohee Choi, Junhyeong Lee, Seunghwa Ryu

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST）） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；agentic(abstract)；分类 cs.AI

AI总结 本文提出CGMas多智能体框架，可自动完成聚合物粗粒度分子动力学的拓扑构建等全流程，完成27项任务，22项密度匹配度在5%内，模拟时间大幅缩短，确立了智能体式LLM用于聚合物粗粒化的可行性。

Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations

用于带旋转的鲁棒终身多智能体路径规划的搜索辅助联合智能体-环境强化学习

He Jiang, Jingtian Yan, Yulun Zhang, Yimin Tang, Tanishq Duhan, Rishi Veerapaneni, Guillaume Sartoretti, Jiaoyang Li

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.AI

AI总结 针对带旋转约束的鲁棒终身多智能体路径规划难题，提出搜索辅助联合强化学习方法，通过结合Causal PIBT与联合优化智能体-环境策略，在高密度地图及混合现实仓库环境中取得显著性能提升。

Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application

面向时间敏感型应用的在线流量调度的多智能体强化学习

Marcos Carvalho, Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci, Daniel F. Macedo

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(abstract)；分类 cs.AI

AI总结 针对动态XR驱动的MEC场景中TSN调度的挑战，本文提出基于HAPPO算法的MARL框架，将各TSN队列建模为自主智能体，可降低平均帧等待时间最多26.8%、最坏情况延迟约16.8%。

OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality

OrchestraBench：评估多智能体编排的故障模式、恢复能力与分解质量

Yidian Chen, Yingzi Gu, Natan Vidra, Spurthi Setty, Sharon Zheng

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；workflow(abstract)；分类 cs.AI

AI总结 OrchestraBench 是评估多智能体编排故障模式、恢复能力与分解质量的基准，通过可控故障注入揭示了不同路由策略、智能体模式的故障处理差异及级联规律。

Comments 8 pages, 4 figures

AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation

AdaptAgent：一种用于代码适配的多智能体、领域引导推理框架

Xiaokai Rong, Hridya Dhulipala, Aashish Yadavally, Tien N. Nguyen

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.SE

AI总结 本研究提出AdaptAgent框架，通过分工的多智能体实现代码适配，在真实数据集上的语义正确性优于强基线，各智能体对适配效果均有重要作用。

TumorBoard: Evidence-Grounded Multi-Agent Decision Support for Longitudinal Neuro-Oncology

TumorBoard：基于证据的多智能体纵向神经肿瘤学决策支持系统

Yantong Liu, Zheyu Zhang, Runpeng Liu, Mu Xitang, Seong-Yoon Shin, Hyun-Ae Lee

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；planning(abstract)；分类 cs.AI

AI总结 TumorBoard是基于证据的多智能体纵向神经肿瘤学决策支持系统，经360例基准测试，其性能优于现有基线，安全管控模块可有效降低有害建议比例。

Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation

基于多智能体评估的角色扮演语言智能体的对抗性压力测试

Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi, Ravisha De Alwis

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

AI总结 本研究提出模块化多智能体平台，通过多轮对话对角色扮演语言智能体开展对抗性压力测试，揭示单策略测试无法发现的故障模式，相关成果作为开源平台发布以支持AI安全。

Comments 8 pages, 1 figure, 7 tables; accepted and presented at ADScAI Conference 2026, University of Moratuwa, Sri Lanka

AI Agent Economics: Can Autonomous Economic Behavior Emerge among AI Agents under Minimal External Conditions?

智能体经济学：在 minimal 外部条件下，AI 智能体间能否涌现出自发的经济行为？

Lingyun Zhang, Shang Shang

专题命中 多智能体 ：agent(title,abstract)；AI agent(title,abstract)；multi-agent(abstract)；分类 cs.AI

AI总结 该研究探究在无预设策略的情况下，AI 智能体能否涌现经济关系，通过两阶段框架在 GPT 和 DeepSeek 的六智能体世界验证，发现组织源于可执行权利与资源后果，为智能体机制治理审计提供依据。

Comments 8 pages, 4 figures, 3 tables