Huan Gao

Huan Gao, Yongqiang Wang · meta-ai

By spreading phases on the unit circle, desynchronization algorithm is a powerful tool to achieve round-robin scheduling, which is crucial in applications as diverse as media access control of communication networks, realization of analog-to-digital converters, and scheduling of traffic flows in intersections. Driven by the increased application of pulse-coupled oscillators in achieving synchronization, desynchronization of pulse-coupled oscillators is also receiving more attention. In this paper, we propose a phase desynchronization algorithm by rigorously analyzing the dynamics of pulse-coupled oscillators and carefully designing the pulse based interaction function. A systematic proof for convergence to phase desynchronization is also given. Different from many existing results which can only achieve equal separation of firing time instants, the proposed approach can achieve equal separation of phases, which is more difficult to achieve due to phase jumps in pulse-coupled oscillators. Furthermore, the new strategy can guarantee achievement of desynchronization even when some nodes have identical initial phases, a situation which fails most existing desynchronization approaches. Numerical simulation results are provided to illustrate the effectiveness of the theoretical results.

Huan Gao, Yongqiang Wang

Driven by increased applications in biological networks and wireless sensor networks, synchronization of pulse-coupled oscillators (PCOs) has gained increased popularity. However, most existing results address the local synchronization of PCOs with initial phases constrained in a half cycle, and results on global synchronization from any initial condition are very sparse. In this paper, we address global PCO synchronization from an arbitrary phase distribution under chain or directed tree graphs. Our results differ from existing global synchronization studies on decentralized PCO networks in two key aspects: first, our work allows heterogeneous coupling functions, and we analyze the behavior of oscillators with perturbations on their natural frequencies; secondly, rather than requiring a large enough coupling strength, our results hold under any coupling strength between zero and one, which is crucial because a large coupling strength has been shown to be detrimental to the robustness of PCO synchronization to disturbances.

Huan Gao, Yongqiang Wang

Average consensus is key for distributed networks, with applications ranging from network synchronization, distributed information fusion, decentralized control, to load balancing for parallel processors. Existing average consensus algorithms require each node to exchange explicit state values with its neighbors, which results in the undesirable disclosure of sensitive state information. In this paper, we propose a novel average consensus approach for directed graphs which can protect the privacy of participating nodes' initial states without the assistance of any trusted third party or data aggregator. By leveraging the inherent robustness of consensus dynamics to embed privacy in random coupling weights between interacting nodes, our proposed approach can guarantee consensus to the exact value without any error. This is in distinct difference from differential-privacy based average consensus approaches which enable privacy through sacrificing accuracy in obtained consensus value. The proposed approach is able to preserve privacy even when multiple honest-but-curious nodes collude with each other. Furthermore, by encrypting exchanged information, the proposed approach can also provide privacy protection against inference by external eavesdroppers wiretapping communication links. Numerical simulations and hardware experiments on Raspberry Pi boards confirm that the algorithm is lightweight in computation and communication.

Bruce Yang, Xinfeng He, Huan Gao et al.

Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often evaluate performance solely based on task accuracy - overlooking critical factors such as token efficiency, modularity, and scalability in multi-agent environments. To address these limitations, we introduce CodeAgents, a prompting framework that codifies multi-agent reasoning and enables structured, token-efficient planning in multi-agent systems. In CodeAgents, all components of agent interaction - Task, Plan, Feedback, system roles, and external tool invocations - are codified into modular pseudocode enriched with control structures (e.g., loops, conditionals), boolean logic, and typed variables. This design transforms loosely connected agent plans into cohesive, interpretable, and verifiable multi-agent reasoning programs. We evaluate the proposed framework across three diverse benchmarks - GAIA, HotpotQA, and VirtualHome - using a range of representative LLMs. Results show consistent improvements in planning performance, with absolute gains of 3-36 percentage points over natural language prompting baselines. On VirtualHome, our method achieves a new state-of-the-art success rate of 56%. In addition, our approach reduces input and output token usage by 55-87% and 41-70%, respectively, underscoring the importance of token-aware evaluation metrics in the development of scalable multi-agent LLM systems. The code and resources are available at: https://anonymous.4open.science/r/CodifyingAgent-5A86

Minghao Ruan, Huan Gao, Yongqiang Wang

Consensus is fundamental for distributed systems since it underpins key functionalities of such systems ranging from distributed information fusion, decision-making, to decentralized control. In order to reach an agreement, existing consensus algorithms require each agent to exchange explicit state information with its neighbors. This leads to the disclosure of private state information, which is undesirable in cases where privacy is of concern. In this paper, we propose a novel approach that enables secure and privacy-preserving average consensus in a decentralized architecture in the absence of an aggregator or third-party. By leveraging partial homomorphic cryptography to embed secrecy in pairwise interaction dynamics, our approach can guarantee consensus to the exact value in a deterministic manner without disclosing a node's state to its neighbors. In addition to enabling resilience to passive attackers aiming to steal state information, the approach also allows easy incorporation of defending mechanisms against active attackers which try to alter the content of exchanged messages. Furthermore, in contrast to existing noise-injection based privacy-preserving mechanisms which have to reconfigure the entire network when the topology or number of nodes varies, our approach is applicable to dynamic environments with time-varying coupling topologies. This secure and privacy-preservation approach is also applicable to weighted average consensus as well as maximum/minimum consensus under a new update rule. The approach is light-weight in computation and communication. Implementation details and numerical examples are provided to demonstrate the capability of our approach.