The paper proposes a Recursive Autonomous Agent (RAA) framework for intelligent manufacturing, combining goal-driven autonomous agents with a recursive organizational structure. It identifies individual autonomy and collective coordination as coupled mechanisms that enable local decision-making and alignment with shared goals. The framework uses goal and capability contracts to define local objectives and facilitate the composition of production units, allowing coordinated groups to function as units within larger organizations.
By Yuning Chen, Hongda Zhang, Linqiang Hu, Ziqing Zhou, Yi Liu, Zhao Huang, Ding Zhou, Haining Xu
The article reviews how large language models (LLMs) enable industrial agents to move beyond predefined workflows toward autonomous planning and execution in smart manufacturing. It identifies five key challenges, defines the concept and core characteristics of industrial agents, and presents a unified taxonomy covering application scenarios, embodiment forms, and capability levels. The authors propose a four‑layer system architecture with core modules for closed‑loop task execution, review representative applications across the industrial lifecycle, and outline future research directions.
By Lei Ren, Haiteng Wang, Shixiang Li, Jing Zhang, Yuqing Wang, Jingwei Guo, Yunfei Zhu, Yuanjun Laili, Yang Tang, Lihui Wang
arXiv:2609.16075v1 Announce Type: cross
Abstract: Flexible robotic production requires joint decisions on process progression, material routing, resource assignment, temporary cooperation, and simult...
By Fouad Bahrpeyma, David Heik, Dirk Reichelt
The paper introduces Automated Multi-Agent Organization Design (AMOD), a framework that treats the organization of agents as a design object and uses an execution-driven loop to iteratively refine responsibilities and coordination rules. AMOD assigns functional responsibilities to agent teams, evaluates outcomes and interaction traces, and revises the organization to address missing, duplicated, or ineffective roles. The approach also proposes testing responsibilities by removal or replacement to validate their necessity.
By Shao-Jun Xia, Yuner Zhang, Huixin Zhang, Di Wang, Yifan Jiang, Liangxi Liu
arXiv:2608. 07148v1 Announce Type: new Abstract: Modern manufacturing imposes six coupled demands on adaptive control: local decisions with global consequences, partial observability, nonstationarity, reflex speed response with long horizon effects, delayed and diffuse outcomes, and dynamics that resist explicit modeling.
By Fouad Bahrpeyma, Dirk Reichelt
arXiv:2606. 12835v1 Announce Type: cross Abstract: The rapid emergence of autonomous AI agents is transforming artificial intelligence from isolated model inference into distributed systems of reasoning, communication, and action.
By Quanyan Zhu
arXiv:2608. 10153v1 Announce Type: new Abstract: Enterprises are deploying autonomous AI agents faster than they can govern them, and prevailing approaches stretch a single discipline, typically DevSecOps built for deterministic automation, across every scale of agency.
By Srinivas Telukunta, Georgios Nektarios Lilis, Lucio Baron
The paper introduces The Trinity, a recursive self‑improvement framework for multimodal agents that couples world generation with harness evolution through three roles: Creator, Explorer, and Evolver. By shifting task organization from surface categories to shared capability requirements, it builds a hierarchical capability tree and a reusable harness tree, enabling efficient transfer learning across heterogeneous tasks. Experiments show the evolved harnesses improve mean performance by 34 points on 28 training benchmarks and 26 points on 18 unseen benchmarks, including two real‑world embodied tasks.
By Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang, Ziyu Guo, Haodong Li, Zhengbo Jiao, Zhiqing Cui, Xinxiang Yin, Shuo Liang, Zhenglin Wan, Hongzhan Lin, Wangbo Zhao Kaipeng Zhang, Pengfei Zhou, Odin Zhang, Yang You
Agensh is a new multi‑agent harness that eliminates a central orchestrator by letting workers self‑organize through a continuous cooperation loop. The system uses a shared workspace, message interface, and shared context to coordinate tasks, verify results, and merge progress asynchronously. Experiments on ProgramBench and pandoc show that scaling from 1 to 1,024 agents improves test‑pass rates by up to 49% relative, demonstrating that agent count is a viable scaling dimension for complex tasks.
By Zhihao Zhan, Ting Song, Li Dong, Shaohan Huang, Jianxun Lian, Yan Xia, Furu Wei
arXiv:2607. 17331v1 Announce Type: new Abstract: Enterprise Resource Planning (ERP) systems record transactions reliably but still delegate almost all operational decision-making to human specialists, because classical rule-based automation cannot reason about exceptions and monolithic AI assistants degrade when asked to coordinate across functional boundaries.
By Zhihao Liu, Tianyu Wang, Xi Vincent Wang, Lihui Wang
arXiv:2609.11737v2 Announce Type: replace-cross
Abstract: Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artifici...
By Zhengran Ji, Jonathan Hyun, Boyuan Chen
arXiv:2608. 05159v1 Announce Type: new Abstract: Enterprise operations extensively rely on multiple heterogeneous business systems and information applications, which also result in severe data silos and process fragmentation.
By Xi Wang, Kun Li, Xianyao Ling, Gang Yin, Liang Zhang, Jiang Wu, Wenbo Lei, Jun Xu, Annie Wang, Fu Zhang, Weizhe Wang