A key component to a MoE model is the routing (gating) strategy.

We also devise a reinforcement learning algorithm for SICMDPs that we call SI-CRL.

We introduce a novel framework for efficient sampling from complex, unnormalised target distributions by exploiting multiscale dynamics. Traditional score-based sampling methods either rely on learned approximations of the score function or involve computationally expensive nested Markov chain Monte Carlo (MCMC) loops. In contrast, the proposed approach leverages stochastic averaging within a slow-fast system of stochastic differential equations (SDEs) to estimate intermediate scores along a diffusion path without training or inner-loop MCMC. Two algorithms are developed under this framework: MultALMC, which uses multiscale annealed Langevin dynamics, and MultCDiff, based on multiscale controlled diffusions for the reverse-time Ornstein-Uhlenbeck process. Both overdamped and underdamped variants are considered, with theoretical guarantees of convergence to the desired diffusion path. The framework is extended to handle heavy-tailed target distributions using Student's t-based noise models and tailored fast-process dynamics. Empirical results across synthetic and real-world benchmarks, including multimodal and high-dimensional distributions, demonstrate that the proposed methods are competitive with existing samplers in terms of accuracy and efficiency, without the need for learned models.

Expected improvement (EI) is one of the most widely used acquisition functions in Bayesian optimization (BO). Despite its proven empirical success in applications, the cumulative regret upper bound of EI remains an open question. In this paper, we analyze the classic noisy Gaussian process expected improvement (GP-EI) algorithm. We consider the Bayesian setting, where the objective is a sample from a GP. Three commonly used incumbents, namely the best posterior mean incumbent (BPMI), the best sampled posterior mean incumbent (BSPMI), and the best observation incumbent (BOI) are considered as the choices of the current best value in GP-EI. We present for the first time the cumulative regret upper bounds of GP-EI with BPMI and BSPMI. Importantly, we show that in both cases, GP-EI is a no-regret algorithm for both squared exponential (SE) and Matérn kernels. Further, we present for the first time that GP-EI with BOI either achieves a sublinear cumulative regret upper bound or has a fast converging noisy simple regret bound for SE and Matérn kernels. Our results provide theoretical guidance to the choice of incumbent when practitioners apply GP-EI in the noisy setting. Numerical experiments are conducted to validate our findings.

Large Language Models (LLMs) have made significant strides in reasoning tasks through methods like chain-of-thought (CoT) reasoning. However, they often fall short in tasks requiring precise computations. Tool-Integrated Reasoning (TIR) has emerged as a solution by incorporating external tools into the reasoning process. Nevertheless, the generalization of TIR in improving the reasoning ability of LLM is still unclear. Additionally, whether TIR has improved the model's reasoning behavior and helped the model think remains to be studied. We introduce ReasonZoo, a comprehensive benchmark encompassing nine diverse reasoning categories, to evaluate the effectiveness of TIR across various domains. Additionally, we propose two novel metrics, Performance-Aware Cost (PAC) and Area Under the Performance-Cost Curve (AUC-PCC), to assess reasoning efficiency. Our empirical evaluation demonstrates that TIR-enabled models consistently outperform their non-TIR counterparts in both mathematical and non-mathematical tasks. Furthermore, TIR enhances reasoning efficiency, as evidenced by improved PAC and AUC-PCC, indicating reduced overthinking and more streamlined reasoning. These findings underscore the domain-general benefits of TIR and its potential to advance LLM capabilities in complex reasoning tasks.

This study proposes a dynamic coupling-informed trajectory optimization algorithm for free-floating space manipulator systems (SMSs). Dynamic coupling between the base and the manipulator arms plays a critical role in influencing the system's behavior. While prior research has predominantly focused on minimizing this coupling, often overlooking its potential advantages, this work investigates how dynamic coupling can instead be leveraged to improve trajectory planning. Singular value decomposition (SVD) of the dynamic coupling matrix is employed to identify the dominant components governing coupling behavior. A quantitative metric is then formulated to characterize the strength and directionality of the coupling and is incorporated into a trajectory optimization framework. To assess the feasibility of the optimized trajectory, a sliding mode control-based tracking controller is designed to generate the required joint torque inputs. Simulation results demonstrate that explicitly accounting for dynamic coupling in trajectory planning enables more informed and potentially more efficient operation, offering new directions for the control of free-floating SMSs.

Next-generation mobile networks must reconcile the often-conflicting goals of multiple service owners. However, today's network slice controllers remain rigid, policy-bound, and unaware of the business context. We introduce Agoran Service and Resource Broker (SRB), an agentic marketplace that brings stakeholders directly into the operational loop. Inspired by the ancient Greek agora, Agoran distributes authority across three autonomous AI branches: a Legislative branch that answers compliance queries using retrieval-augmented Large Language Models (LLMs); an Executive branch that maintains real-time situational awareness through a watcher-updated vector database; and a Judicial branch that evaluates each agent message with a rule-based Trust Score, while arbitrating LLMs detect malicious behavior and apply real-time incentives to restore trust. Stakeholder-side Negotiation Agents and the SRB-side Mediator Agent negotiate feasible, Pareto-optimal offers produced by a multi-objective optimizer, reaching a consensus intent in a single round, which is then deployed to Open and AI RAN controllers. Deployed on a private 5G testbed and evaluated with realistic traces of vehicle mobility, Agoran achieved significant gains: (i) a 37% increase in throughput of eMBB slices, (ii) a 73% reduction in latency of URLLC slices, and concurrently (iii) an end-to-end 8.3% saving in PRB usage compared to a static baseline. An 1B-parameter Llama model, fine-tuned for five minutes on 100 GPT-4 dialogues, recovers approximately 80% of GPT-4.1's decision quality, while operating within 6 GiB of memory and converging in only 1.3 seconds. These results establish Agoran as a concrete, standards-aligned path toward ultra-flexible, stakeholder-centric 6G networks. A live demo is presented https://www.youtube.com/watch?v=h7vEyMu2f5w\&ab_channel=BubbleRAN.