Earticle

Negotiation is a process of reaching an agreement on the terms of a transaction, such as price, quantity, for two or more parties. Negotiation tries to maximize the benefits for all parties concerned. Instead of using human-based negotiation, the e-commerce environment provides such an environment as adopting automated negotiation. Thus, choosing agent technology is appropriate for an automatic electronic negotiation platform, since autonomous software agents strive for the best deal on behalf of the human participants. Negotiation agents need a clear-cut definition of negotiation models or strategies. In reality, most bargaining systems embody nearly one negotiation model. In this article, we present a mobile agent negotiation system with reusable negotiation strategies that allows agents to dynamically embody a user’s favorite negotiation strategy which can be preinstalled as a component in the system. We develop a prototype system, which is fully implemented in compliance with FIPA specifications, and then, describe the benefits of using the system.

대형 언어 모델의 발전으로 코드 자동 생성뿐만 아니라 코드 리팩토링까지 자동화하려는 시도가 활 발히 이루어지고 있다. 그러나 단일 모델이 전체 리팩토링 과정을 처리하는 방식은 구조적 한계와 기 능 보존의 어려움을 가지는 문제를 야기한다. 본 논문은 이러한 문제를 해결하고자 역할 분담형 멀팉 에이전트 구조를 기반으로 한 코드 리팩토링 자동화 시스템을 설계하고 구현하였다. 각 에이전트는 분 석, 수정, 검증, 리뷰를 독립적으로 수행하며, 실제 리팩토링 과제를 통해 자동화 흐름과 품질 평가 체 계를 구성하였다.

본 논문은 다중 에이전트 강화학습 방식을 사용하여 입력 데이터로부터 분류에 효과적인 특징 집합을 찾아내는 방식을 제안한다. 기계 학습 분야에 있어서 분류에 적합한 특징들을 찾아내는 것은 매우 중요하다. 데이터에는 수많은 특징들이 존재할 수 있으며, 여러 특징들 중 일부는 분류나 예측에 효과적일 수 있지만 다른 특징들은 잡음 역할을 함으 로써 올바른 결과를 생성하는 데에 오히려 악영향을 줄 수 있다. 기계 학습 문제에서 분류나 예측 정확도를 높이기 위한 특징 선택은 매우 중요한 문제 중 하나이다. 이러한 문제를 해결하기 위해 강화학습을 통한 특징 선택 방법을 제시한다. 각각의 특징들은 하나의 에이전트를 가지게 되며, 이 에이전트들은 특징을 선택할 것인지 말 것인지에 대한 여부를 결정 한다. 에이전트들에 의해 선택된 특징들과 선택되지 않은 특징들에 대해서 각각 보상을 구한 뒤, 보상에 대한 비교를 통해 에이전트의 Q-value 값을 업데이트 한다. 두 하위 집합에 대한 보상 비교는 에이전트로 하여금 자신의 행동이 옳은지에 대한 판단을 내릴 수 있도록 도와준다. 이러한 과정들을 에피소드 수만큼 반복한 뒤, 최종적으로 특징들을 선별한다. 이 방법을 통해 Wisconsin Breast Cancer, Spambase, Musk, Colon Cancer 데이터 세트에 적용한 결과, 각각 0.0385, 0.0904, 0.1252, 0.2055의 정확도 향상을 보여주었으며, 최종적으로 0.9789, 0.9311, 0.9691, 0.9474 의 분류 정확도를 보여주었다. 이는 우리가 제안한 방법이 분류에 효과적인 특징들을 잘 선별하고 분류에 대한 정확도를 높일 수 있음을 보여준다.

In this paper, we propose a method for finding feature subsets that are effective for classification in an input dataset by using a multi-agent reinforcement learning method. In the field of machine learning, it is crucial to find features suitable for classification. A dataset may have numerous features; while some features may be effective for classification or prediction, others may have little or rather negative effects on results. In machine learning problems, feature selection for increasing classification or prediction accuracy is a critical problem. To solve this problem, we proposed a feature selection method based on reinforced learning. Each feature has one agent, which determines whether the feature is selected . After obtaining corresponding rewards for each feature that is selected, but not by the agents, the Q-value of each agent is updated by comparing the rewards. The reward comparison of the two subsets helps agents determine whether their actions were right. These processes are performed as many times as the number of episodes, and finally, features are selected. As a result of applying this method to the Wisconsin Breast Cancer, Spambase, Musk, and Colon Cancer datasets, accuracy improvements of 0.0385, 0.0904, 0.1252 and 0.2055 were shown, respectively, and finally, classification accuracies of 0.9789, 0.9311, 0.9691 and 0.9474 were achieved, respectively. It was proved that our proposed method could properly select features that were effective for classification and increase classification accuracy.

In this work, we model multi-user distributed channel access as a game with channels and users, and propose the Multi-Agent Thompson Sampling (MA-TS) algorithm. It uses Bayes’ theorem to dynamically optimize action selection. This optimization aims to maximize throughput. We derive the algorithm’s computational complexity as . Simulations show that MA-TS converges to a pure strategy Nash equilibrium (PNE) and outperforms existing methods in average throughput.

In CRNs, it is crucial to develop an efficient and reliable spectrum detector that consistently provides accurate information about the channel state. In this work, we investigate a CSS in a fully-distributed environment where all secondary users (SUs) are equipped with directional antennas and make decisions based solely on their local knowledge without information sharing between SUs. First, we establish a stochastic sequential optimization problem, which is an NP-hard, that maximizes the SU’s detection accuracy by the dynamic and optimal control of the energy sensing/detection threshold. It can enable SUs to select an available channel and sector without causing interference to the primary network. To address it in a distributed environment, the problem is transformed into a decentralized partially observed Markov decision process (Dec-POMDP) problem. Second, in order to determine the best control for the Dec-POMDP in a practical environment without any prior knowledge of state?action transition probabilities, we develop a multi-agent deep deterministic policy gradient (MADDPG)-based algorithm, which is referred to as MA-DCSS. This algorithm adopts the centralized training and decentralized execution (CTDE) architecture. Third, we analyzed its computational complexity and showed the proposed approach’s scalability by the polynomial computational complexity, in terms of the number of channels, sectors, and SUs. Lastly, the simulation confirms that the proposed scheme provides enhanced performance in terms of convergence speed, accurate detection, and false alarm probabilities when it is compared to baseline algorithms.

In B5G heterogeneous cellular networks, a rapid increase in the number of small cell base stations (SBSs) to support a massive number of devices tends to waste a considerable amount of energy. Therefore, intelligent management of SBSs’ power consumption is one of the most important research issues. We herein propose quasi-distributed Q-learning-based cell breathing (QD-QCB) considering full and partial SBS collaborations for maximizing network energy efficiency. Also, the concept of an aggregated active SBS set based on regional user distributions is proposed for computing- and energy-efficient operation. Through intensive simulations, we show that the proposed QD-QCB algorithm can achieve optimal energy efficiency, and improve the network energy efficiency significantly compared with conventional algorithms such as no transmit power control, random cell breathing, and greedy cell breathing algorithms.

This paper investigates the Contention Window (CW) optimization problem in multi-agent scenarios, where the fully cooperative among mobile stations is considered. A partially observable environment is employed to model and analyze the CW optimization problem, and Smart Exponential-Threshold-Linear with Deep Q-learning Network (SETL-DQN) Multi-Agent (MA) algorithm is proposed to obtain the optimal system throughput through the CW Threshold optimization. In the determined scenarios, SETL-DQN(MA) can effectively cope with the mutual interaction among mobile stations. The simulation results show that our proposed method is superior from both static and dynamic scenarios and has the highest optimum packet transmission efficiency.

This paper proposes an Adversarial-Aware Multi-Agent Deep Deterministic Policy Gradient (AA-MADDPG) framework integrating adversarial risk analysis with deep reinforcement learning for robust resource allocation and offloading in heterogeneous aerial access networks. We model adversarial behavior using three rationality paradigms, including Nash equilibrium, level-k thinking, and prospect maximizing, employing Bayesian model averaging for robust adversarial action prediction. The framework enables collaborative decision-making among aerial access tiers and IoT devices while maintaining attack resilience. Simulations demonstrate that AA-MADDPG reduces task drop rates by 27% and energy consumption by 19% compared to baselines.

This study introduces the Multi-Agent, Multi-Parameter, Interaction-Driven Contention Window Optimization (M2I-CWO) algorithm, a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework designed to optimize multiple CW parameters in IEEE 802.11 Wireless LANs. Unlike single-parameter or specialized multi-agent methods, M2I-CWO employs a Dueling-DQN architecture and an Adaptive Interaction Reward Function?spanning independent, cooperative, competitive, and mixed modes?and accommodates Hierarchical Multi-Agent System (HMAS) or Federated RL (FRL) for further scalability. First, multiple CW parameters are simultaneously adjusted to enhance collision management. Second, M2I-CWO consistently achieves throughput improvements in both static and dynamic scenarios. Extensive results confirm M2I-CWO's superiority in efficiency and adaptability.

In this study, we analyze the dynamic characteristics of the Cucker-Smale model with heterogeneous free will (CSF). Most existing research has examined flocking when external perturbations converge to identical values; however, we investigate the case in which agents have different free-will vectors. We first prove that a positive lower bound exists for velocity differences between agents with heterogeneous free will. This implies that flocking cannot occur in the CSF. In particular, in the case of a nontrivial initial velocity and free will, we demonstrate that the distance between agents increases linearly with time. We also obtain an explicit upper bound for the maximum distance between agents when the communication rate is greater than zero and less than 1/2. The maximum distance growth rate depends on the communication rate. Finally, we validate the theoretical results through numerical simulations.

In order to ensure second-order multi-agent systems (MAS) realizing consensus more quickly in a limited time, a new protocol is proposed. In this new protocol, the gradient algorithm of the overall cost function is introduced in the original protocol to enhance the connection between adjacent agents and improve the moving speed of each agent in the MAS. Utilizing Lyapunov stability theory, graph theory and homogeneity theory, sufficient conditions and detailed proof for achieving a finite-time consensus of the MAS are given. Finally, MAS with three following agents and one leading agent is simulated. Moreover, the simulation results indicated that this new protocol could make the system more stable, more robust and convergence faster when compared with other protocols.

This study investigates the problem of leader-following consensus for multi-agent systems with output saturations. This study assumes that the agents are described as a neutrally stable system, and the leader agent generates the bounded trajectory within the saturation level. Then, the objective of the leader-following consensus is to track the trajectory of the leader by exchanging information with neighbors. To solve this problem, we propose an observer-based distributed consensus algorithm. Then, we provide a consensus analysis by applying the Lyapunov stability theorem and LaSalle's invariance principle. The result shows that the agents achieve the leader-following consensus in a global sense. Moreover, we can achieve the consensus by choosing any positive control gain. Finally, we perform a numerical simulation to demonstrate the validity of the proposed algorithm.

Designing a reward function is a critical challenge in reinforcement learning. However, as environments become more complex and tasks grow more difficult, designing a reward function that drives optimal behavior becomes increasingly challenging. To overcome these issues, Preference based reinforcement learning has proposed methods that learn reward functions based on the preference between two trajectories, thereby eliminating the need for handcrafted reward function. In multi-agent reinforcement learning, the challenge is even greater due to the complex interactions among agents, which makes designing a single global reward function even more difficult. In this paper, we show that when a single global reward function is learned via preference-based reinforcement learning in multi-agent setting, it often fails to capture sufficient information for optimal policy learning. Instead, we propose a method for learning individual reward functions that provide additional guidance for each agent’s optimal policy. Our approach, which leverages graph structures and preference-based reinforcement learning, outperforms the method based on learning a single, global reward function.

The growing complexity of 5G/6G, IoT, and edge networks exposes the limits of single-agent LLM control in scalability, real-time performance, and reliability. Multi-Agent Systems (MAS) combined with LLMs offer a path forward. This paper surveys state-of-the-art LLM-based MAS for network management. We propose a taxonomy that re-interprets the Centralized/Decentralized/Hybrid split under two networking-specific axes (a strict LLM-core inclusion criterion and an anchoring on the NetOps lifecycle), complemented by a role-based lens (Coordinator, Translator, Negotiator). We finally identify key challenges such as hallucination and inference latency, and outline directions toward trustworthy autonomous networks.

Diabetic nephropathy (DN) remains a leading cause of end-stage renal disease (ESRD), driven by chronic inflammation, oxidative stress, and apoptosis. Current therapies targeting glycemic and blood pressure control fail to address the underlying molecular mechanisms of DN. This study investigates the therapeutic potential of andrographolide (AD), a diterpenoid lactone from Andrographis paniculata, in mitigating DN by modulating key molecular pathways. Through integrative network pharmacology, molecular docking, and in vivo/in vitro experiments, 107 overlapping DN-related targets were identified, with STAT3, PI3K, and AKT1 emerging as core nodes. Molecular docking revealed high binding affinities between AD and these targets, supporting its modulatory potential. In vivo, AD significantly improved renal function in streptozotocin-induced DN rats, reducing proteinuria, glomerular hypertrophy, and renal fibrosis. AD also attenuated oxidative stress, decreased pro-inflammatory cytokine levels, and enhanced antioxidant enzyme activities, demonstrating systemic anti-inflammatory and antioxidative effects. In vitro studies further confirmed that AD alleviates podocyte oxidative stress and apoptosis under high glucose conditions by suppressing the RAGE-NF-κB and STAT3/PI3K/Akt pathways. Histological analyses revealed substantial improvements in renal architecture, including reductions in fibrosis and mesangial expansion. These results underscore AD's multi-target mechanism, directly addressing DN's core pathological drivers, including inflammation, oxidative stress, and apoptosis. As a natural compound with notable safety and efficacy, AD holds promise as an adjunct or standalone therapeutic agent for DN. This study establishes a robust preclinical foundation for AD, warranting further exploration in clinical trials and its potential application in other diabetic complications.