4 accepted papers
Multi-robot systems can greatly enhance efficiency through coordination and collaboration, yet in practice, full-time communication is rarely available and interactions are constrained to close-range exchanges. Existing methods either maintain all-time connectivity, rely on fixed schedules, or adopt
Multi-robot systems can greatly enhance efficiency through coordination and collaboration, yet in practice, full-time communication is rarely available and interactions are constrained to close-range exchanges. Existing methods either maintain all-time connectivity, rely on fixed schedules, or adopt…
Recent work has explored training Large Language Model (LLM) search agents with reinforcement learning (RL) for open-domain question answering. However, most evaluations focus solely on final answer accuracy, overlooking how these agents reason with and act on external evidence. We introduce **SeekB…
Differentially Private Federated Learning (DP-FL) is a promising paradigm for training models on large-scale decentralized data under Differential Privacy (DP) guarantees which confronts two challenges: 1) providing a privacy guarantee without sacrificing model performance; 2) tackling system hetero…