Process supervision has emerged as a promising approach for enhancing LLM reasoning, yet existing methods fail to distinguish meaningful progress from mere verbosity, leading to limited reasoning capabilities and unresolved token inefficiency.To address this, we propose Stage-aware Hierarchical Advantage via Potential Estimation (SHAPE), a framework that formalizes reasoning as a trajectory through a state space of empirical solvability.SHAPE introduces a hierarchical credit assignment mechanism: at the segment level, it employs a stageaware advantage function to prioritize efficient breakthroughs in low-potential states; at the token level, it utilizes entropy-driven redistribution to sharpen execution signals.Extensive experiments in math reasoning across three base models and five benchmarks demonstrate that SHAPE achieves an average accuracy gain of 3% with 30% reduced token consumption.

Federated Learning (FL) is a promising machine learning paradigm for collaborative training on cross-soils in a privacy-protected manner. However, the existence of non-IID data causes problems such as performance degradation and thus becomes one of the key challenges in FL recently. To address this problem, we propose a clustered personalized federated learning method named as SynCPFL. SynCPFL groups clients sharing with the similar data distribution together, thereby facilitating collaboration and producing a better-personalized model for each client. In contrast to existing clustered federated learning methods, SynCPFL does not require multiple rounds of interaction between clients and server, so that the communication overhead is reduced a lot, thereby saving resources of clients. We evaluate SynCPFL on benchmark datasets, the experimental results demonstrate that SynCPFL outperforms existing methods.

Abstract As a promising architecture of next‐generation network, software defined‐information centric network (SD‐ICN) inherits the advantages of software defined network (SDN) and information‐centric network (ICN) to enable flexible and fast content retrieval, especially in the current era of artificial intelligence. However, the existing researches mainly focus on a single respective in this field, which motivates in comprehensively providing a forward‐looking guidance and development direction for scholars and engineers. To this end, the latest developments of SD‐ICN is presented. First, the widely‐accepted concepts and impacts on traditional networks are introduced. Second, the shortcomings of SDN and ICN over conventional networks are respectively analyzed to illustrate the necessity of SD‐ICN. Third, based on extensive analysis and deep deliberation, a methodical taxonomy for existing combination studies is proposed. They are divided into SDN over ICN, ICN over SDN, and mutual immersive pattern. Fourth, the performances of three integration categories are compared and the limitations of related works are highlighted. Fifth, the maturity index from six development indicators are evaluated. Further, the maturity and practicality of these schemes are generalized. Based on the above studies and comparisons, the lessons learned by SDN and ICN developments are concluded. Finally, future research directions and opportunities are discussed for the readers.

The evolution of cyber-physical system (CPS) benefits from substantial supports of many cutting-edge technologies. However, as a significant medium to bridge virtual and reality parts, the dependability of various network components is facing unprecedented challenges and threats. In this article, we propose a smart collaborative balancing (SCB) scheme to dynamically adjust the orchestration of network functions and efficiently optimize the workflow patterns. First, mathematical models of bandwidth allocation for multiuser with appropriate probability distribution are established. Matrix operations are utilized to solve the relevant issues based on individual congestion windows. Invasion defense mechanisms are also provided and discussed. Second, specific procedures of collaboration among different network components are presented. The capabilities of CPS, in terms of bandwidth allocation and invasion defense, are guaranteed via novel queueing policies and access control mechanisms. Third, we build a comprehensive prototype including multiple domains and users for validations. Experimental results in two scenarios illustrate that SCB not only supports service reliability of end hosts with different priorities, but also resists malicious attacks which are targeting the corresponding terminals inside domains. Compared to the benchmarks in software defined networks and traditional Internet, our scheme performs better in both available resource management and abnormal flow recognition aspects.

Artificial intelligence is being utilized in multipath industrial networks to enhance service supporting ability. However, existing obstacles in controlling receive buffer restrict throughput even when higher bandwidth is available. Therefore, in this article, we propose a smart collaborative automation (SCA) scheme to improve resource usage and overcome buffer limitations. First, a mathematical model is established to describe primary system operations with considerations of chunk loss. The inf-supremum methodology and probability theory are adopted to track congestion window variations. Second, differences in disordered chunk expectations are analyzed to locate the critical condition of round numbers. Specific algorithm details are provided via simplifying comparison to achieve comprehensive policy selections. Third, evaluation topologies and environments are created with reasonable parameter settings. Validation results demonstrate that model-driven SCA can reduce unexpected occupations at the receiver-side. Comparing to intuition-driven schemes, overall performances, in terms of the sender's transmission capacity and receiver's buffer utilization, are improved under different experimental configurations.