The emergence of Large Language Models (LLMs) in Multi-Agent Systems (MAS) has opened new possibilities for artificial intelligence, yet current implementations face significant challenges in resource management, task coordination, and system efficiency. While existing frameworks demonstrate the potential of LLM-based agents in collaborative problem-solving, they often lack sophisticated mechanisms for parallel execution and dynamic task management. This paper introduces DynTaskMAS, a novel framework that orchestrates asynchronous and parallel operations in LLM-based MAS through dynamic task graphs. The framework features four key innovations: (1) a Dynamic Task Graph Generator that intelligently decomposes complex tasks while maintaining logical dependencies, (2) an Asynchronous Parallel Execution Engine that optimizes resource utilization through efficient task scheduling, (3) a Semantic-Aware Context Management System that enables efficient information sharing among agents, and (4) an Adaptive Workflow Manager that dynamically optimizes system performance. Experimental evaluations demonstrate that DynTaskMAS achieves significant improvements over traditional approaches: a 21-33% reduction in execution time across task complexities (with higher gains for more complex tasks), a 35.4% improvement in resource utilization (from 65% to 88%), and near-linear throughput scaling up to 16 concurrent agents (3.47× improvement for 4× agents). Our framework establishes a foundation for building scalable, high-performance LLM-based multi-agent systems capable of handling complex, dynamic tasks efficiently.

Data aggregation management is paramount in data-driven distributed systems. Conventional solutions premised on centralized networks grapple with security challenges concerning authenticity, confidentiality, integrity, and privacy. Recently, distributed ledger technology has gained popularity for its decentralized nature to facilitate overcoming these challenges. Nevertheless, insufficient identity management introduces risks like impersonation and unauthorized access. In this paper, we propose Degator, a data aggregation management framework that leverages self-sovereign identity and functions in decentralized networks to address security concerns and mitigate identity-related risks. We formulate fully decentralized aggregation protocols for data persistence and acquisition in Degator. Degator is compatible with existing data persistence methods, and supports cost-effective data acquisition minimizing dependency on distributed ledgers. We also conduct a formal analysis to elucidate the mechanism of Degator to tackle current security challenges in conventional data aggregation management. Furthermore, we showcase the applicability of Degator through its application in the management of decentralized neuroscience data aggregation and demonstrate its scalability via performance evaluation.

Decentralized finance (DeFi) is revolutionizing the traditional centralized finance paradigm with its attractive features such as high availability, transparency, and tamper-proofing. However, attacks targeting DeFi services have severely damaged the DeFi market, as evidenced by our investigation of 80 real-world DeFi incidents from 2017 to 2022. Existing methods, based on symbolic execution, model checking, semantic analysis, and fuzzing, fall short in identifying the most DeFi vulnerability types. To address the deficiency, we propose Context-Sensitive Concolic Verification (CSCV), a method of automating the DeFi vulnerability finding based on user-defined properties formulated in temporal logic. CSCV builds and optimizes contexts to guide verification processes that dynamically construct context-carrying transition systems in tandem with concolic executions. Furthermore, we demonstrate the effectiveness of CSCV through experiments on real-world DeFi services and qualitative comparison. The experiment results show that our CSCV prototype successfully detects 76.25% of the vulnerabilities from the investigated incidents with an average time of 253.06 seconds.

Surface electromyography (sEMG), the electrical signals generated by muscle activity, plays an important role in prosthetics, orthotics, and human-computer interaction because of its non-invasive signal acquisition, real-time responsiveness, and ability to provide rich information for decoding complex movements. However, the complexity and nonlinear characteristics of sEMG signals present challenges in implementing sEMG-based tasks, such as hand gesture classification. Motivated by effectively addressing the challenges and extending the applicability of sEMG signals, we propose a nearest-centroid-based hand gesture classification framework using sEMG signals. We utilize the Dynamic Time Warping Barycenter Averaging (DBA) algorithm to generate centroids of sEMG signals and leverage Dynamic Time Warping (DTW) to measure signal discrepancies. Our pipeline features an effective data preprocessing approach and a heuristic, repeatable, optimal parameter search process. Additionally, our framework supports interpretability analysis using Shapley values. Through our extensive experiments, we demonstrate that our framework has achieved an average accuracy of 90.0% and a peak accuracy of 91.25% on a public dataset Mendeley data-sEMG, which outperforms the surveyed existing methods and establishes our framework as state-of-the-art on such dataset.