Yichuan Jiang

TIST Journal 2026 Journal Article

Autonomous Domain Adaptation Self-Optimization Approach for Cross-Domain Industrial Agents

• Tian-Yu Zuo
• Kai Di
• Pan Li
• Yichuan Jiang

In the heterogeneous and dynamically evolving Industrial Internet, industrial agents are required to possess cross-domain adaptability and self-learning capabilities to facilitate task generalization and scalable deployment across diverse operational contexts. However, existing domain adaptation approaches predominantly rely on static feature alignment or domain-invariant assumptions, lacking a systematic consideration of working condition variability and the interplay between self-learning and adaptation. This oversight hampers their effectiveness in real-world industrial scenarios, where agents must operate under complex conditions with limited target domain knowledge. Consequently, these methods often suffer from knowledge shift and insufficient policy generalization. To address these limitations, this article introduces the instance weighting-based domain-adaptive optimization (IW-DAO) framework. IW-DAO combines an instance weighting-based knowledge alignment mechanism with a Bayesian optimization strategy, forming a dynamic self-learning loop tailored for cross-domain adaptation. Specifically, the framework constructs an adaptive knowledge representation in a high-dimensional invariant feature space and formulates a cross-domain performance evaluation estimator to guide the unsupervised learning of knowledge transfer and adaptive optimization via Bayesian iterative search. Extensive experiments on industrial asset management tasks as well as a real-world industrial flow process dataset with various operating conditions demonstrate the effectiveness of IW-DAO. The proposed framework enables industrial agents to evolve autonomously and be deployed efficiently across diverse domains. IW-DAO consistently outperforms baseline and expert-tuned methods, demonstrating strong generalization and adaptability in both industrial asset management and complex flow process scenarios.

TIST Journal 2026 Journal Article

Chain Disruption Risk-Oriented Task Migration in Multiplex Networked Industrial Chains

• Kai Di
• Tian-Yu Zuo
• Pan Li
• Jiuchuan Jiang
• Yichuan Jiang

In industrial production processes, disruptions within the industrial chain can severely affect the collaborative capabilities of production agents. A notable example occurred during the COVID-19 pandemic, when many agents faced interruption risks and were unable to participate in coordinated production. Ensuring continuity under such conditions requires migrating tasks from disrupted agents to viable alternatives. Designing effective task migration strategies, however, must account for the emergent multiplex nature of modern industrial chains. In these multiplex networked industrial chains, disruption risk in one layer can propagate to others, generating cascading failures across the system. This introduces two key challenges: (1) disruption risk creates mismatches not only between product agents and tasks but also across network layers, enlarging the problem dimensionality; and (2) simultaneous disruptions across multiple agents and layers increase the volume of tasks needing migration, greatly expanding the solution space. To address these challenges, we introduce the notion of a multiplex potential field, which captures cross-layer interdependencies and system-level dynamics in multiplex industrial chains. Building on this concept, we develop a hierarchical contextual task migration algorithm that exploits the multiplex potential field to guide both inter-layer and intra-layer task reallocations. Extensive experiments show that our approach consistently achieves superior utility, markedly improves task completion ratios, and reduces execution costs compared to benchmark algorithms. Furthermore, it attains solution quality comparable to that of the optimal CPLEX solver while requiring substantially less computation time. Finally, a case study on the FAO international food trade network demonstrates that the proposed framework is not only theoretically robust but also practically effective when deployed on large-scale real-world multiplex systems.

IJCAI Conference 2025 Conference Paper

Risk-Aware Task Migration for Multiplex Unmanned Swarm Networks in Adversarial Environments

• Kai Di
• Tienyu Zuo
• Pan Li
• Yuanshuang Jiang
• Fulin Chen
• Yichuan Jiang

With the rapid development and deep integration of artificial intelligence and automation technologies, autonomous unmanned swarms dynamically organize into multiplex network structures based on diverse task requirements in adversarial environments. Frequent task variations lead to load imbalances among agents and between network layers, significantly increasing the risk of enemy detection and destruction. Existing approaches typically simplify multiplex networks into single-layer structures for task scheduling, failing to address these load imbalance issues. Moreover, the coupling between task dynamics and network multiplexity dramatically increases the complexity of designing task migration strategies, and it is proven NP-hard to achieve such load balancing. To address these challenges, this paper proposes a risk-aware task migration method that achieves dynamic load balancing by matching task requirements with both intra-layer agent capabilities and inter-layer swarm capabilities. Simulation results demonstrate that our approach significantly outperforms benchmark algorithms in task completion cost, task completion proportion, and system robustness. In particular, the algorithm achieves solutions statistically indistinguishable from the optimal solutions computed by the CPLEX solver, while exhibiting significantly reduced computational overhead.

JAAMAS Journal 2024 Journal Article

Offline policy reuse-guided anytime online collective multiagent planning and its application to mobility-on-demand systems

• Wanyuan Wang
• Qian Che
• Yichuan Jiang

Abstract The popularity of mobility-on-demand (MoD) systems boosts online collective multiagent planning (Online_CMP), where spatially distributed servicing agents are planned to meet dynamically arriving demands. For city-scale MoDs with a fleet of agents, Online_CMP methods must make a tradeoff between computation time (i. e. , real-time) and solution quality (i. e. , the number of demands served). Directly using an offline policy can guarantee real-time, but cannot be dynamically adjusted to real agent and demand distributions. Search-based online planning methods are adaptive, but are computationally expensive and cannot scale up. In this paper, we propose a principled Online_CMP method, which reuses and improves the offline policy in an anytime manner. We first model MoDs as a collective Markov Decision Process ( \({\mathbb {C}}\) -MDP) where the collective behavior of agents affects the joint reward. Given the \({\mathbb {C}}\) -MDP model, we propose a novel state value function to evaluate the policy, and a gradient ascent (GA) technique to improve the policy. We further show that offline GA-based policy iteration (GA-PI) can converge to global optima of \({\mathbb {C}}\) -MDP under certain conditions. Finally, with real-time information, the offline policy is used as the default plan, GA-PI is used to improve it and generate an online plan. Experimental results show that our offline policy reuse-guided Online_CMP method significantly outperforms standard online multiagent planning methods on MoD systems like ride-sharing and security traffic patrolling in terms of computation time and solution quality.

AAMAS Conference 2023 Conference Paper

Structural Credit Assignment-Guided Coordinated MCTS: An Efficient and Scalable Method for Online Multiagent Planning

• Qian Che
• Wanyuan Wang
• Fengchen Wang
• Tianchi Qiao
• Xiang Liu
• Jiuchuan Jiang
• Bo An
• Yichuan Jiang

Online planning has been widely focused in many areas, such as industry chain and collective intelligence. Due to the trade-off nature of trading computation time for solution quality, Monte-Carlo tree search (MCTS) methods have shown great success in online planning. However, the exponential growth of global joint-action space makes it challenging to apply MCTS to online multiagent planning (MAP). Our goal in this paper is to design an efficient and scalable coordinated MCTS method for online MAP. Combining with coordination graphs, recent Factored Value MCTS (FV-MCTS) has attempted to recover the trade-off property for MCTS-based online MAP. However, FV-MCTS directly uses the global payoff to reward each agent, and has difficulty in finding coordination actions in multiagent MCTS settings where other agents are also taking exploratory actions. We overcome this limitation by designing a generalized structural credit assignment (SCA)-guided coordinated MCTS, where SCA is used to promote coordination and MCTS is used to search promising global joint-actions. Specially, we use the Shapley value to provide a fair SCA, which can be efficiently computed by exploiting locality of interaction between agents. Moreover, theoretical analysis shows that the proposed method can bound the bias of the estimated value of the global join-action under certain conditions. Finally, we conduct extensive experiments in some typical sequential multiagent coordination domains such as multi-robot warehouse patrolling in industry chain, etc. to validate the efficiency and scalability of the proposed method over other benchmarks. ∗corresponding author. Proc. of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023), A. Ricci, W. Yeoh, N. Agmon, B. An (eds.), May 29 – June 2, 2023, London, United Kingdom. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). All rights reserved.

TIST Journal 2022 Journal Article

A Foraging Strategy with Risk Response for Individual Robots in Adversarial Environments

• Kai Di
• Yifeng Zhou
• Fuhan Yan
• Jiuchuan Jiang
• Shaofu Yang
• Yichuan Jiang

As an essential problem in robotics, foraging means that robots collect objects from a given environment and return them to a specified location. On many occasions, robots are required to perform foraging tasks in adversarial environments, such as battlefield rescue, where potential adversaries may damage robots with a certain probability. The longer an individual robot moves through adversarial environments, the higher the probability of being damaged by adversaries. The robot system can gain utility only when the robot brings carried objects back to a predetermined home station. Such a risk of being damaged makes returning home at different locations potentially relevant to the expected utility produced by the robot. Thus, the individual robot faces a dilemma when it responds to the potential risks in adversarial environments: whether to return the carried resources home or continue foraging tasks. In this article, two fundamental environment settings are discussed, homogeneous cases and heterogeneous cases. The former is analyzed as having both the optimal substructure property and the non-aftereffect property. Then, we present a dynamic programming (DP) algorithm that can find an optimal solution with polynomial time complexity. For the latter, it is proven that finding an optimal solution is \( \mathcal {NP} \) -hard. We then propose a heuristic algorithm: A division hierarchical path planning (DHPP) algorithm that is based on the idea of dividing the foraging routes generated initially into a certain number of subroutes to dilute risks. Finally, these algorithms are extensively evaluated in simulations, concluding that in adversarial environments, they can significantly improve the productivity of an individual robot before it is damaged.

AAMAS Conference 2022 Conference Paper

Online Collective Multiagent Planning by Offline Policy Reuse with Applications to City-Scale Mobility-on-Demand Systems

• Wanyuan Wang
• Gerong Wu
• Weiwei Wu
• Yichuan Jiang
• Bo An

The popularity of mobility-on-demand (MoD) systems boosts the need for online collective multiagent planning, where spatially distributed servicing agents are planned to meet dynamically arriving demands. For city-scale MoDs with a population of agents, it is necessary to find a balance between computation time (i. e. , realtime) and solution quality (i. e. , the number of demands served). Directly using an offline policy can guarantee real-time, but cannot be dynamically adjusted to real agent and demand distributions. On the other hand, search-based online planning methods are adaptive. However, they are computationally expensive and cannot scale up. In this paper, we propose a principled online multiagent planning method, which reuses and improves the offline policy in an anytime manner. We first model MoDs as a collective Markov Decision Process (C-MDP) where the history collective behavior of agents affects the joint reward. We propose a novel state value function to evaluate the policy, and a gradient ascent (GA) technique to improve the policy. We show that GA-based policy iteration (GA-PI) on local policy can converge. Finally, given real-time information, the offline policy is used as the default plan and GA-PI is used to improve it and generate an online plan. Experimentally, the proposed offline policy reuse method significantly outperforms standard online multiagent planning methods on MoD systems like ride-sharing and security traffic patrolling in terms of computation time and solution quality.

IS Journal 2021 Journal Article

Enhancing the Quality in Crowdsourcing E-Markets Through Team Formation Games

• Bing Ai
• Wanyuan Wang
• Minghui Hua
• Yichuan Jiang
• Jiuchuan Jiang
• Yifeng Zhou

Crowdsourcing e-markets have been widely used to complete various complex tasks with the help of seamlessly integrating the ubiquitous intelligent systems and artificial intelligence. Most of traditional crowdsourcing e-markets focus primarily on individual incentives to motivate workers to participate. However, workers generally have heterogeneous values, which brings forth an undesirable outcome that workers with larger values monopolize a fixed total payment. This monopolization discourages the workers with smaller values from participating, thereby severely reducing the quality of individual-oriented crowdsourcing e-markets. Thus, this article proposes a team formation (TF) games-based mechanism in which workers are incentivized to form teams and obtain payments according to their contributions. Moreover, the existence of Nash equilibrium for a given TF game is rigorously analyzed. Finally, the experimental results in terms of both simulated and realistic datasets demonstrate that, as compared with state-of-the-art methods, our mechanism can achieve higher crowdsourcing e-markets quality.

TAAS Journal 2021 Journal Article

Risk-aware Collection Strategies for Multirobot Foraging in Hazardous Environments

• Kai Di
• Yifeng Zhou
• Jiuchuan Jiang
• Fuhan Yan
• Shaofu Yang
• Yichuan Jiang

Existing studies on the multirobot foraging problem often assume safe settings, in which nothing in an environment hinders the robots’ tasks. In many real-world applications, robots have to collect objects from hazardous environments like earthquake rescue, where possible risks exist, with possibilities of destroying robots. At this stage, there are no targeted algorithms for foraging robots in hazardous environments, which can lead to damage to the robot itself and reduce the final foraging efficiency. A motivating example is a rescue scenario, in which the lack of a suitable solution results in many victims not being rescued after all available robots have been destroyed. Foraging robots face a dilemma after some robots have been destroyed: whether to take over tasks of the destroyed robots or continue executing their remaining foraging tasks. The challenges that arise when attempting such a balance are twofold: (1) the loss of robots adds new constraints to traditional problems, complicating the structure of the solution space, and (2) the task allocation strategy in a multirobot team affects the final expected utility, thereby increasing the dimension of the solution space. In this study, we address these challenges in two fundamental environmental settings: homogeneous and heterogeneous cases. For the former case, a decomposition and grafting mechanism is adopted to split this problem into two weakly coupled problems: the foraging task execution problem and the foraging task allocation problem. We propose an exact foraging task allocation algorithm, and graft it to another exact foraging task execution algorithm to find an optimal solution within the polynomial time. For the latter case, it is proven \( \mathcal {NP} \) -hard to find an optimal solution in polynomial time. The decomposition and grafting mechanism is also adopted here, and our proposed greedy risk-aware foraging algorithm is grafted to our proposed hierarchical agglomerative clustering algorithm to find high-utility solutions with low computational overhead. Finally, these algorithms are extensively evaluated through simulations, demonstrating that compared with various benchmarks, they can significantly increase the utility of objects returned by robots before all the robots have been stopped.

AAMAS Conference 2019 Conference Paper

Efficient City-Scale Patrolling Using Decomposition and Grafting

• Wanyuan Wang
• Zichen Dong
• Bo An
• Yichuan Jiang

This paper uses an integer program (IP) to formulate the city-scale patrolling (CSP) problem, with the objective of maximizing the police visibility rate (PVR) and the constraint of incident response time guarantee. We decompose the original CSP into two subproblems: minimizing police problem (MinP) and maximizing PVR (MaxP) problem. A polynomial time approximation algorithm is proposed for MinP, and a polynomial time optimal algorithm is proposed for MaxP. We conduct experiments to demonstrate the efficiency of the proposed algorithm.

AAAI Conference 2018 Conference Paper

Optimal Spot-Checking for Improving Evaluation Accuracy of Peer Grading Systems

• Wanyuan Wang
• Bo An
• Yichuan Jiang

Peer grading, allowing students/peers to evaluate others’ assignments, offers a promising solution for scaling evaluation and learning to large-scale educational systems. A key challenge in peer grading is motivating peers to grade diligently. While existing spot-checking (SC) mechanisms can prevent peer collusion where peers coordinate to report the uninformative grade, they unrealistically assume that peers have the same grading reliability and cost. This paper studies the general Optimal Spot-Checking (OptSC) problem of determining the probability each assignment needs to be checked to maximize assignments’ evaluation accuracy aggregated from peers, and takes into consideration 1) peers’ heterogeneous characteristics, and 2) peers’ strategic grading behaviors to maximize their own utility. We prove that the bilevel OptSC is NP-hard to solve. By exploiting peers’ grading behaviors, we first formulate a single level relaxation to approximate OptSC. By further exploiting structural properties of the relaxed problem, we propose an efficient algorithm to that relaxation, which also gives a good approximation of the original OptSC. Extensive experiments on both synthetic and real datasets show significant advantages of the proposed algorithm over existing approaches.

TAAS Journal 2018 Journal Article

Understanding Crowdsourcing Systems from a Multiagent Perspective and Approach

• Jiuchuan Jiang
• Bo An
• Yichuan Jiang
• Donghui Lin
• Zhan Bu
• Jie Cao
• Zhifeng Hao

Crowdsourcing has recently been significantly explored. Although related surveys have been conducted regarding this subject, each has mainly consisted of a review of a single aspect of crowdsourcing systems or on the application of crowdsourcing in a specific application domain. A crowdsourcing system is a comprehensive set of multiple entities, including various elements and processes. Multiagent computing has already been widely envisioned as a powerful paradigm for modeling autonomous multi-entity systems with adaptation to dynamic environments. Therefore, this article presents a novel multiagent perspective and approach to understanding crowdsourcing systems, which can be used to correlate the research on crowdsourcing and multiagent systems and inspire possible interdisciplinary research between the two areas. This article mainly discusses the following two aspects: (1) The multiagent perspective can be used for conducting a comprehensive survey on the state of the art of crowdsourcing, and (2) the multiagent approach can bring about concrete enhancements for crowdsourcing technology and inspire future research directions that enable crowdsourcing research to overcome the typical challenges in crowdsourcing technology. Finally, this article discusses the advantages and disadvantages of the multiagent perspective by comparing it with two other popular perspectives on crowdsourcing: the business perspective and the technical perspective.

AAMAS Conference 2017 Conference Paper

Protecting Elections with Minimal Resource Consumption

• Yunpeng Li
• Yichuan Jiang
• Weiwei Wu

In democratic elections, malicious agents may attempt to control elections to achieve their own goals. To guarantee impartiality, it is necessary to protect the election outcomes from control. In this paper, we consider how to protect election outcome from control using minimal resources. We assume malicious agents attempt to prevent a specific candidate from winning a democratic election with plurality rule through denial-of-service (deletion) attacks on voter groups (e. g. , polling places). First, we show that the problem is NP-hard. Second, we propose a (|C|-1)-approximation algorithm for the problem, where |C| is the number of candidates. Finally, we validate the efficiency of our approximation algorithm based on simulation experiments.

AAMAS Conference 2017 Conference Paper

Pursuing a Faster Evader Based on an Agent Team with Unstable Speeds

• Fuhan Yan
• Yichuan Jiang

Previous studies of multiagent pursuit-evasion problem usually assume that the pursuers can move at stable speeds. However, in many real cases, the pursuers’ speeds may be unstable. In this paper, we study multiagent pursuit-evasion problem based on pursuers with unstable speeds in a continuous open world. We present a feasible pursuing strategy, and the experimental results show that our strategy can generally lead to higher capture success ratios than previous strategies in the situations where the pursuers’ speeds are unstable.

AAMAS Conference 2016 Conference Paper

Truthful Team Formation for Crowdsourcing in Social Networks (Extended Abstract)

• Wanyuan Wang
• Zhanpeng He
• Peng Shi
• Weiwei Wu
• Yichuan Jiang

We study complex task crowdsourcing by team formation in social networks (SNs), where the requester wishes to hire a group of socially close workers that can work together as a team. The workers are selfish that can manipulate the crowdsourcing system by providing unreal private information, which will discourage other workers from participation and is unprofitable for the requester. This paper develops two efficient truthful mechanisms for the small- and largescale social team crowdsourcing applications, to guarantee each worker’s profit is optimized by behaving truthfully.

JAAMAS Journal 2015 Journal Article

Cross-layers cascade in multiplex networks

• Zhaofeng Li
• Fuhan Yan
• Yichuan Jiang

Abstract The study of information cascade in multiplex networks, where agents are connected by using multiple linking types, has received increasing attention. Compared with the cascade in simplex networks, a noticeable characteristic of the cascade in multiplex networks is that information may be spread between multiple layers. In this study, we focus on the cross-layers cascade, which helps clarify two opposing opinions about the information cascade in multiplex networks: multiplexity can speed up or slow down information cascade. The linear threshold model is generalized into multiplex networks as conjoint agents become active, if the influences of active neighbors in any layer reach a predefined threshold. The preconditions and reasons for the slow-down and speed-up phenomena are discussed using four representative case studies and theoretical analyses. Next, analytical results are validated by using extensive simulations in which the multiplex networks are generated by random, small-world and scale-free network models. It is found that the slow-down phenomenon emerges due to the obstruction of cross-layers cascade which connects the distributed shortest path in multiple layers and the inhibitory effect of negative influence. Conversely, extra short paths or rapid spreading in one additional layer can facilitate the cascade process in existing networks, respectively. Extensive simulations also show that multiplex networks consisting of different network models are more competent for the cascade process compared with multiplex networks generated by a single network model. In conclusion, the concept of cross-layers cascade may elucidate the additional study of information spreading in multiplex networks.

IJCAI Conference 2015 Conference Paper

Environment-Driven Social Force Model: Lé vy Walk Pattern in Collective Behavior

• Danyan Lv
• Zhaofeng Li
• Yichuan Jiang

Animals in social foraging not only present the ordered and aggregated group movement but also the individual movement patterns of Lévy walks that are characterized as the power-law frequency distribution of flight lengths. The environment and the conspecific effects between group members are two fundamental inducements to the collective behavior. However, most previous models emphasize one of the two inducements probably because of the great difficulty to solve the behavior conflict caused by two inducements. Here, we propose an environment-driven social force model to simulate overall foraging process of an agent group. The social force concept is adopted to quantify the conspecific effects and the interactions between individuals and the environment. The cohesion-first rule is implemented to solve the conflict, which means that individuals preferentially guarantee the collective cohesion under the environmental effect. The obtained results efficiently comply with the empirical reports that mean the Lévy walk pattern of individual movement paths and the high consistency and cohesion of the entity group. By extensive simulations, we also validate the impact of two inducements for individual behaviors in comparison with several classic models.

TAAS Journal 2015 Journal Article

Reliable Task Allocation with Load Balancing in Multiplex Networks

• Yichuan Jiang
• Yifeng Zhou
• Yunpeng Li

In multiplex networks, agents are connected by multiple types of links; a multiplex network can be split into more than one network layer that is composed of the same type of links and involved agents. Each network link type has a bias for communicating different types of resources; thus, the task’s access to the required resources in multiplex networks is strongly related to the network link types. However, traditional task allocation and load balancing methods only considered the situations of agents themselves and did not address the effects of network link types in multiplex networks. To solve this problem, this article considers both link types and agents, and substantially extends the existing work by highlighting the effect of network layers on task allocation and load balancing. Two multiplex network-adapted models of task allocation with load balancing are presented: network layer-oriented allocation and agent-oriented allocation. This article also addresses the unreliability in multiplex networks, which includes the unreliable links and agents, and implements a reliable task allocation based on a negotiation reputation and reward mechanism. Our findings show that both of our presented models can effectively and robustly satisfy the task allocation objectives in unreliable multiplex networks; the experiments prove that they can significantly reduce the time costs and improve the success rate of tasks for multiplex networks over the traditional simplex network-adapted task allocation model. Lastly, we find that our presented network layer-oriented allocation performs much better in terms of reliability and allocation time compared to our presented agent-oriented allocation, which further explains the importance of network layers in multiplex networks.

ECAI Conference 2014 Conference Paper

Noised Diffusion Dynamics with Individual Biased Opinion

• Fuhan Yan
• Zhaofeng Li 0001
• Yichuan Jiang

In online social network, the personal information dissemination behavior is reported to be affected by the clash of social individuals' biased opinions. In this paper, we present a model to discuss the influence of individual biased opinion on diffusion dynamics. Based on multi-agent simulations, we obtain some conclusions which are helpful for recommender systems and in controlling diffusion. In addition, our study offers potential avenues for the study of diffusion dynamics with personal biases.

AAMAS Conference 2012 Conference Paper

Cooperation among Malicious Agents: A General Quantitative Congestion Game Framework

• Zaojie Rui
• Tuanjie Fu
• Darong Lai
• Yichuan Jiang

Malicious behaviors and cooperation have been well studied separately. However, rare systematic study has been conducted on the combination of them: malicious cooperation. In this paper, a general quantitative utility function of malicious cooperation is firstly formulated in a congestion game framework. Both objective and subjective factors are incorporated (e. g. , malicious social networks and moral degrees). Then, Nash equilibrium and the condition of malicious cooperation are given theoretically. Meanwhile, we show empirically that malicious cooperation may even improve system performance (i. e. , catfish effect).

AAMAS Conference 2008 Conference Paper

Convergence at Prominent Agents: A Non-Flat Synchronization Model of Situated Multi-Agents

• Jiuchuan Jiang
• Yichuan Jiang

This paper presents a novel non-flat synchronization model where the synchronization capacity of each agent is different regarding its social rank and strategy dominance. In the presented model, the prominent agents may have higher synchronization forces, and finally the collective synchronization results may incline to converge at such prominent agents’ strategies, which is called prominence convergence in collective synchronization and proved by our experimental results. The presented model can well match the peculiarities of real multi-agent societies where each agent plays a different role in the synchronization, and make up the restrictions of related benchmark works that only concerned about the flat synchronization.

IJCAI Conference 2007 Conference Paper

• Yichuan Jiang
• Toru Ishida

Social law is perceived as evolving through the competition of individual social strategies held by the agents. A strategy with strong authority, accepted by many agents, will tend to diffuse to the remaining agents. The authority of a social strategy is determined by not only the number of but also the collective social positions of its overlaid agents. This paper presents a novel collective strategy diffusion model in agent social law evolution. In the model, social strategies that have strong authority are impressed on the other agents. The agents will accept (partially or in full) or reject them based on their own social strategies and social positions. The diffusion of social strategies proceeds in a series of steps and the final result depends on the interplay between the forces driving diffusion and the counteracting forces.

AAMAS Conference 2007 Conference Paper

Agent Coordination by Trade-off between Locally Diffusion Effects and Socially Structural Influences

• Yichuan Jiang
• Jiuchuan Jiang
• Toru Ishida

There were always two separated methods to make agent coordination: individual-local balance perspective and individualsociety balance perspective. The first method only considered the balance between individual agents and their local neighbors; the second method only considered the balance between individual agents and the whole multi-agent society. However, in reality, the agents will be diffused by their local neighbors as well as influenced by their social contexts simultaneously; therefore, it is necessary to deal with the social performance as well as local performance. To address such problem this paper presents an agent coordination method in an integrative model where we combine the two perspectives together and make trade-off between them. With our presented model, the individual, local and social concerns can be balanced well in a unified and flexible manner. Moreover, the experimental results show that there are often situations in which the two coordination perspectives aren't conflictive but often bring out the better in each other.