Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets. We present the first end-to-end framework for safety verification of learned multi-agent communication policies through policy abstraction: neural policies are distilled into interpretable decision trees, then formally verified, with empirical validation confirming that verified safety properties transfer to original networks.
arXiv:2607. 15003v1 Announce Type: new Abstract: The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.
By Riccardo Curcio, Toni Mancini, Enrico Tronci
arXiv:2608.29490v1 Announce Type: cross
Abstract: Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collis...
By Joe Eappen, Zikang Xiong, Shreyash S. Iyengar, Suresh Jagannathan
arXiv:2606. 23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes these models opaque and difficult to analyze formally, rendering them intractable for existing verification tools.
By Davide Corsi, Kyungmin Kim, Roy Fox
arXiv:2607. 16210v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a major barrier to deployment.
By Luca Marzari, Ezio Bartocci, Enrico Marchesini
arXiv:2606. 18308v1 Announce Type: cross Abstract: Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics.
By Zijie Meng, Ziwei Li, Yufei Liu, Zhiyu Li, Jiyuan Liu, Wenhua Nie, Bingcai Wei, Miao Zhang
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
arXiv:2607. 13655v1 Announce Type: new Abstract: Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios.
By Celeste Veronese, Edoardo Zorzi, Daniele Meli, Alessandro Farinelli
arXiv:2607. 14093v1 Announce Type: new Abstract: This paper presents a novel three level hierarchical learning architecture for autonomous UAV swarms performing search and rescue operations.
By Oleksii Bychkov
arXiv:2606. 05395v1 Announce Type: cross Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior.
By Yunhao Yang, Neel P. Bhatt, Kevin Wang, Samuel Tetteh, Zhangyang Wang, Ufuk Topcu
arXiv:2607. 23870v1 Announce Type: cross Abstract: Smart-city airspace is transforming Uncrewed Aerial Vehicles (UAVs) from passive sensing platforms into cyber-physical decision makers that must follow operational rules under degraded observations and ambiguous language.
By Belal S. Alsinglawi, Weizheng Wang, Junyi Wu, Yi Jiang, Lianhai Lin, Merouane Debbah, Izzat Alsmadi
The paper introduces a finite‑sample probabilistic safety certification framework for black‑box AI decision models used in closed‑loop grid operation. It transforms the AI‑grid evaluation into a binary unsafe outcome under a safety specification and applies exact binomial inference to provide a tight one‑sided upper bound on the unsafe operation probability, using held‑out calibration scenarios. The framework also incorporates physically interpretable sample‑space adversarial attacks to address distribution shifts and is validated through case studies involving 1,000‑agent AI models for grid‑edge flexibility coordination.
By Yihong Zhou, Hanbin Yang, Thomas Morstyn