The paper introduces ORCH, a method that applies human organizational theory to create task‑specific hierarchical structures for large, heterogeneous embodied AI teams. Using ORCH, teams of up to 50 agents across 25 wildfire‑response missions outperformed four existing multi‑agent frameworks, achieving higher mission scores and greater execution efficiency. Both human‑designed and language‑model‑generated ORCH organizations improved performance, with hierarchical organization preserving concurrent activity while coordinating ordered transitions between mission phases.
By Zhengran Ji, Jonathan Hyun, Boyuan Chen
The paper introduces ORCH, a method that applies human organization theory to create task‑specific hierarchical structures for large, heterogeneous embodied AI teams. By combining concurrent and sequential interdependence, ORCH outperforms four existing multi‑agent frameworks across 25 wildfire‑response missions, improving mission outcomes, execution efficiency, exploration, and computational resource use. Both human‑designed and language‑model‑generated ORCH organizations yield significant performance gains, with hierarchical organization enabling sustained concurrent activity and coordinated transitions in long‑horizon missions.
arXiv:2510.26915v2 Announce Type: replace-cross
Abstract: While heterogeneous teams have typically been designed for well-specified missions with known semantics, generative intelligence, i.e., large...
By Zachary Ravichandran, Fernando Cladera, Ankit Prabhu, Jason Hughes, Carlos Nieto-Granda, Varun Murali, Camillo Taylor, George J. Pappas, Vijay Kumar
The paper introduces a Cognitive Multi-Agent Framework that uses Language-Grounded Hierarchical Reinforcement Learning (LG‑HRL) to coordinate UAV and UGV agents in search and rescue (SAR) tasks. Natural language instructions are processed by a large language model into semantic cues that guide high‑level strategy selection and role assignment, supported by a shared cognitive workspace. Experiments in a simulated disaster environment show that LG‑HRL speeds learning 2.3×, boosts coordination coherence by 37%, improves subgoal accuracy and hazard avoidance, and raises victim rescue rates by 20‑30%.
By Sepideh Ravanbakhsh, Hamidreza Moradi
AeroWeaver is a new embodied‑agent harness that integrates large language model (LLM) decision making with the executable skills of individual UAVs, enabling distributed, adaptive swarm execution. It connects semantic mission decisions to governed skills, organizes role‑conditioned local agents for coordination, and refines skill selection online using role‑indexed state‑action‑reward experience. Experiments demonstrate that AeroWeaver maintains valid skill execution without a central joint‑action generator and supports reward‑guided, training‑free adaptive learning from accumulated execution experience.
By Jiabin Lou, Yirong Yang, Haopeng Wang, Xuxin Lv, Xinyu Liu, Diyuan Hou, Xuehong Liu, Rongye Shi, Wenjun Wu
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
Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared objectives through local perception, information exchange, and coordinated action. UAV swarms embody...
The paper introduces Degrees of Freedom (DoF), a continuous framework that measures how much decision-making is delegated to agents in large language model–based multi‑agent systems. By varying DoF, the authors explore a spectrum between fully centralized and fully decentralized coordination, finding that intermediate settings often outperform both extremes across several task domains. The study shows that task characteristics and retained experience influence how coordination granularity affects performance, offering empirical guidance for designing hybrid coordination regimes.
By Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu, Yi Han, Yangyang Zheng, Hao Wang, Qian Li, Chengwei Qin
SwarmWorld demonstrates that homogeneous language‑model agents can self‑organize into evolving technological societies without assigned roles or direct communication. In a spatial environment, agents explore, process resources, construct artifacts, and write executable controllers that are later evaluated by a deterministic simulator. The resulting societies develop broader, more resilient technological portfolios than isolated search, with agents differentiating into exploration, construction, maintenance, and coordination roles as the world matures.
By Subhadeep Pal, Fiona Y. Wang, Markus J. Buehler
arXiv:2609.22682v1 Announce Type: new
Abstract: Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unkno...
By Aneesh Pappu, Mirac Suzgun, Yongchan Kwon, Federico Bianchi, Batu El, Mykel J. Kochenderfer, Hancheng Cao, James Zou
arXiv:2606. 31966v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded environments remains underexplored.
By Qingyun Liu, Jiwen Zhang, Jingyi Hu, Siyuan Wang, Zhongyu Wei
arXiv:2607. 25446v1 Announce Type: new Abstract: Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol).
By Huan Chen, Xiang Song, Jian Jin, Pan Ren, Liang-Jie Zhang