arXiv:2604.01213v1 Announce Type: new
Abstract: Efficient robotic extraterrestrial exploration requires robots with diverse capabilities, ranging from scientific measurement tools to advanced locomotion. A robotic team enables the distribution of task…
arXiv:2512.02079v2 Announce Type: replace
Abstract: Coordinating emergency responses in extreme environments, such as wildfires, requires resilient and high-bandwidth communication backbones. While autonomous aerial swarms can establish ad-hoc network…
arXiv:2604.00449v1 Announce Type: new
Abstract: We study distributed optimization over networks with Byzantine agents that may send arbitrary adversarial messages. We propose \emph{Gradient Tracking with Probabilistic Edge Dropout} (GT-PD), a stochast…
arXiv:2604.00284v1 Announce Type: new
Abstract: We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills in knowledge retrieval, summarization and awar…
arXiv:2604.00523v1 Announce Type: new
Abstract: We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been…
arXiv:2604.00319v1 Announce Type: new
Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or …
arXiv:2510.06141v4 Announce Type: replace
Abstract: Convergence in high-probability (HP) has attracted increasing interest, due to implying exponentially decaying tail bounds and strong guarantees for individual runs of an algorithm. While many works …
arXiv:2604.00249v1 Announce Type: new
Abstract: Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role…
arXiv:2604.00433v1 Announce Type: cross
Abstract: This letter studies multi-agent reinforcement learning in partially observable Markov potential games. Solving this problem is challenging due to partial observability, decentralized information, and t…
arXiv:2604.00477v1 Announce Type: cross
Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessments, and if so, how many are needed? Through 960 sessi…