Jan 2026· Research· Vol abs/2609.22967· 0 citations· 104 references
Computer Science
TL;DR
This review offers a unified synthesis of collaboration architectures and topologies, neural-communication co-design that treats the channel as a differentiable pipeline component, embodied action-perception loops via multi-agent reinforcement learning, and resilience mechanisms for synchronization, uncertainty quantification, and label-efficient learning.
Abstract
Multi-agent unmanned systems are moving from isolated, ego-centric sensing toward collaborative intelligence, in which distributed agents exchange compact features to overcome a local observation trap that no single agent can escape: occlusions, finite sensor range, and environmental degradation. The field has matured across architectural, communication, embodied, resilience, and trust dimensions, yet existing surveys examine these dimensions in isolation and rarely expose the dependencies among them. This review offers a unified synthesis through 2 complementary lenses. The first is a 5-dimensional taxonomy spanning collaboration stage, communication paradigm, fusion architecture, learning strategy, and application domain. The second is a set of 3 cognitive synergy conditions—Semantic Disambiguation, Pragmatic Information Exchange, and Proactive Informational Foraging—that turn the notion of cognitive synergy into operational criteria. Across these lenses, we survey collaboration architectures and topologies, neural-communication co-design that treats the channel as a differentiable pipeline component, embodied action-perception loops via multi-agent reinforcement learning, and resilience mechanisms for synchronization, uncertainty quantification, and label-efficient learning. We then map these advances onto 4 operational domains—V2X, unmanned aerial, industrial logistics, and smart cities—and onto the safety–privacy–utility triad. To counter benchmark saturation and evaluation fragmentation, we propose GCI-Bench, a 5-pillar scoring protocol with a maturity model that makes the trade-offs of collaborative methods comparable across studies. A critical reflection on reproducibility, the sim-to-real gulf, and conditions under which collaboration degrades performance identifies open challenges and charts directions toward general collaborative intelligence under real-world uncertainty.
Initially homogeneous LLM agents in SwarmWorld self-organize without assigned roles or recipes into evolving technological societies, which develop broader, more resilient technological portfolios than a strong best-of-N isolated-search baseline.
Subhadeep Pal, F. Y. Wang, Markus J. Buehler· 5 citations
SAIGE, a lightweight multi-agent collaboration mechanism based on Semantic-Aware Incremental Graph Evolution, is proposed, suggesting that multi-agent superiority is bounded by task structure rather than universal, and that more agents do not necessarily make a system more intelligent.
The Multi-Objective State-Action Network (MOSAN), an autonomous cognitive information fusion framework designed for robust cross-campaign generalization and sensor shift adaptation, establishes a scalable and rigorous paradigm for autonomous biophysical discovery.
S. Domenico, B. Guilcapi, A. Milano et al.· Machine Learning: Science an...· 0 citations
With the progressive evolution of physical entities at the network edge into embodied intelligent agents, the paradigm of network intelligence is shifting from isolated processing to Agentic AI collaboration. As a cornerstone for transcending the physical sensing limits of individual agents and enabling swarm intellige...
Tian-Ge Fu, Pu-Yi Yao, Shen-Yuan Ren et al.· IEEE Transactions on Cogniti...· 0 citations
This survey unifies the literature within a six-stage closed-loop framework comprising observation, contextualization, reasoning and prediction, planning and orchestration, execution and collaboration, and feedback and resilience and uses this framework to review advances in multimodal intelligence, large language mode...
Kai Li, Cong-Gai Li, S. A. Siddiqui et al.· 1 citation
A key contribution is an LLM-assisted architecture in which a base-station-hosted agent conducts global network reasoning and autonomously reconfigures access and backhaul infrastructure, and illustrates how this agentic-AI-driven approach can transform UAVs from task-specific platforms into a continuously evolving com...
Zhao-Yang Li, Xin Jin, Zi-Jiu Yang et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 18, 2026
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.