近年來隨著對於大型軟體系統需要的增加，開放式多代理人系統逐漸被重視並成為一個提供滿足此需求之系統平台，而在建立此平台之研究領域中，代理人組織之觀念被廣泛的採用並成為此平台之建構基礎。為了形成代理人組織，代理人動態角色的扮演儼然成為一個重要且關鍵的一環。然而，對於動態角色的扮演存在著以下幾個重要的問題：(一)代理人組織如何在開放的環境中尋找到代理人；(二)代理人組織如何在多個代理人中選擇適合的代理人來扮演角色；(三)代理人如何透過角色的扮演來合作以達成組織的目的；(四)當代理人欲離開組織時如何脫去所扮演的角色。在本論文中，我們提出了以下兩個方法：(一)我們提出了動態角色扮演生命週期來闡述上述之問題，並延伸簽約網路協定發展了一個結合評價模型之協定，稱之為以代理人為中心之簽約網路協定；(二)我們提出了一個風險支援評價模型來促進協定中代理人之選擇，並利用兩個實驗來驗證此模型。

As open multi-agents systems are getting increasing attentions in building large-scale software systems, the study on agent organizations -- a building block of multi-agents systems, becomes a promising research track. Roles as a first class citizen in agent organizations impose an imperious demand for dealing with the major challenge: how agents bind roles in the formation of agent organizations in which agents can dynamically enter or leave the organizations. This challenge can be further boiled down to four issues: how to discover agents distributed over various
organizations, how to select reliable agents to bind roles, how to enable agents to cooperate on roles binding, and how to unbind roles as agents leave an organization. The focus of this dissertation is two-fold: (1) an extension to Contract Net protocol with reputation model to address these four issues related to the lifecycle of dynamic role binding, called Agent-centric Contract Net Protocol (ACNP), as a negotiation mechanism that agents can adopt to establish agent organizations at run time through roles binding; and 2) a risk-enabled reputation model, called REAL, to facilitate the decision making of agents selection in ACNP, which is validated through two empirical experiments.

[1] FIPA ACL specifications. In The Foundation for Intelligent Physical Agents (FIPA), 2002.
[2] OWL-S: Semantic markup for web services. In http://www.daml.org/services/owl-s/, 2003.
[3] Universal description discovery and integration (UDDI) version 3.0. In http://www.uddi.org/, 2005.
[4] M. Ankerst, M. M. Breunig, H.-P. Kriegel, and J. Sander. OPTICS: Ordering points to identify the clustering structure. In Proceedings of ACM SIGMOD’99, 1999.
[5] A. Avila-Rosas and M. Luck. A direct reputation model for VO formation. In Proceedings of Multi-Agent Systems and Applications IV, 2005.
[6] M. Becht, T. Gurzki, J. Klarmann, and M. Muscholl. ROPE: Role oriented programming environment for multiagent systems. In The 4th Conference on Cooperative Information Systems (CoopIS’99), 1999.
[7] G. Cabri, L. Ferrari, and L. Leonardi. Enabling mobile agents to dynamically assume roles. In Proceedings of the 2003 ACM Symposium on Applied Computing pages, March 2003.
[8] A. Chavez and P. Maes. Kasbah: An agent marketplace for buying and selling goods. In Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi-Agent Technology (PAAM’96), 1996.
[9] M. Dastani, V. Dignum, and F. Dignum. Role-assignment in open agent societies. In Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, July 2003.
[10] V. Dignum, J.-J. Meyer, H. Weigand, and F. Dignum. An organization-oriented model for agent societies. In Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems, 2002.
[11] M. Ester, H.-P. Kriegel, J. Sander, and X. Xu. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96), 1996.
[12] J. Ferber and O. Gutknecht. A meta-model for the analysis and design of organizations in multi-agent systems. In Proceedings of the Third International Conference on Multi-Agent Systems (ICMAS98), pages 128–135, 1998.
[13] J. Ferber, O. Gutknecht, and F. Michel. From agents to organizations: an organizational view of multi-agent systems. In Agent-Oriented Software Engineering IV, 2003.
[14] G. Gottlob, M. Schrefl, and B. Rock. Extending object-oriented systems with roles. ACM Transactions on Information Systems, 14(3):268–296, 1996.
[15] M. Hannoun, O. Boissier, and J. S. Sichman. Moise: An organizational model for multi-agent systems. In Proceedings of IBERAMIA-SBIA’2000, pages 156–165, 2000.
[16] R. Hermoso, H. Billhardt, and S. Ossowski. Integrating trust in virtual organisations. In Proceedings of the Five International Joint Conference on Autonomous Agents and Multi-Agent Systems, pages 121–133, 2006.
[17] K. V. Hindriks, F. S. de Boer, W. van der Hoek, and J.-J. C. Meyer. Agent programming in 3APL. Autonomous Agents and Multi-Agent Systems, 2(4):357–401, 1999.
[18] J. F. H‥ubner, J. S. Sichman, and O. Boissier. A model for the structural, functional, and deontic specification of organizations in multiagent systems. In Proceedings of the 16th Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence, pages 118–128, 2002.
[19] J. F. H‥ubner, J. S. Sichman, and O. Boissier. S-Moise+: A middleware for developing organised multi-agent systems. In International Workshop on Organiztions in Multi-Agent Systems: From Organizations to Organization Oriented Programming (OOOP2005), pages 107–120, 2005.
[20] T. D. Huynh, N. R. Jennings, and N. R. Shadbolt. An integrated trust and reputation model for open multi-agent systems. Autonomous Agents and Multi-Agent Systems, 13(2):119–154, 2006.
[21] P. M. Institute. A Guide to the Project Management Body of Knowledge (PMBOK Guide), Third Edition. ISBN 1-930699-45-X, 2005.
[22] W. C. Jamison and D. Lea. TRUCE: Agent coordination through concurrent interpretation of role-based protocols. In Proceedings of Coordination 99, 1999.
[23] E. A. Kendall. Role modeling for agent system analysis, design, and implemention. IEEE Concurrency, 8(2):34–41, 2000.
[24] T. Knabe, M. Schillo, and K. Fischer. Improvements to the fipa contract net protocol for performance increase and cascading applications. In Proceedings of the Workshop on Multiagent Interoperability, 2002.
[25] J. Lee, S.-P. Ma, S.-J. Lee, Y.-C. Wang, and Y.-Y. Lin. Extending contract net protocol for dynamic binding in service composition. International Journal of Software Engineering and Knowledge Engineering, (to appear).
[26] C. Lema??tre and C. B. Excelente. Multi-agent organization approach. In Proceedings of the second Iberoamerican Workshop on Distributed Artificial Intelligence and Multi- Agent systems, Toledo, Spain, 1998.
[27] D. Martin, M. Burstein, S. McIlraith, M. Paolucci, and K. Sycara. OWL-S and agentbased systems. In Proceedings of Web Services and Agent-Based Systems Engineering, 2004.
[28] D. Nguyen, S. G. Thompson, J. Patel, L. W. Teacy, N. R. Jennings, M. Luck, V. Dang, S. Chalmers, N. Oren, T. J. Norman, A. Preece, P. M. Gray, G. Shercliff, P. J. Stockreisser, J. Shao, W. A. Gray, and N. J. Fiddian. Delivering services by building and running virtual organisations. BT Technology Journal, 24(1):141–152, 2006.
[29] J. J. Odell, H. V. D. Parunak, and B. Bauer. Representing agent interaction protocols in UML. In First International Workshop on Agent-Oriented Software Engineering, 2000.
[30] OMG. Unified modeling language specification version 2.0, August 2005.
[31] M. Paolucci, J. Soudry, N. Srinivasan, and K. Sycara. A broker for OWL-S web services. In Proceedings of the AAAI Spring Symposium, 2004.
[32] S. D. Ramchurn, D. Huynh, and N. R. Jennings. Trust in multi-agent systems. The Knowledge Engineering Review, 19(1):1–25, 2004.
[33] G. J. Ray C.Williams and S. G.Behrens. Software Risk Evaluation (SRE) Method Description (Version 2.0). Software Engineering Institute, Carnegie Mellon University.
[34] T. Reenskaug. Working with objects: The OOram Software Engineering Method. Manning Publications, 1996.
[35] J. Sabater and C. Sierra. Regret: A reputation model for gregarious societies. In Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems, pages 1104–1113, 2002.
[36] J. Sabater and C. Sierra. Social regret, a reputation model based on social relations. ACM SGIecom Exchanges, 3(1):44–56, 2002.
[37] J. Sabater and C. Sierra. Review on computational trust and reputation models. Artificial Intelligence Review, 24(1):33–60, 2005.
[38] J. Sander, X. Qin, Z. Lu, N. Niu, and A. Kovarsky. Automatic extraction of clusters from hierarchical clustering representations. In Proceedings of 7th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD’03), 2003.
[39] T. Sandholm. An implementation of the contract net protocol based on marginal cost calculations. In Proceedings of 11th National Conference on Artificial Intelligence (AAAI-93), July 1993.
[40] T. Sandholm and V. Lesser. Issues in automated negotiation and electronic commerce: Extending the contract net framework. In Proceedings of First International Confer- ence on Multi-agent Systems (ICMAS’95), 1995.
[41] R. G. Smith. The contract net protocol: High-level communication and control in a distributed problem solver. IEEE Transactions on Computers, 29(12):1104–1113, December 1980.
[42] F. Steimann. Role=interface: A merger of concepts. Journal of Object-Oriented Programming, 14(4):23–32, 2001.
[43] C. P. Team. CMMI for Development, version 1.2. SEI, CMU, 2006.
[44] J. Vokˇr’?nek, J. B’?ba, J. Hod’?k, J. Vyb’?hal, and M. Pˇechouˇcek. Competitive contract net protocol. In SOFSEM 2007: Theory and Practice od Computer Science, LNCS 4362, pages 656–668, 2007.
[45] M. Wooldridge, N. R. Jennings, and D. Kinny. The Gaia methodology for agentoriented analysis and design. Autonomous Agents and Multi-Agent Systems, 3(3):285–312, 2000.
[46] L. Xiong and L. Liu. Peertrust: Supporting reputation-based trust for peer-to-peer electronic communities. IEEE Transactions on Knowledge and Data Engineering, 16(7):843–857, 2004.
[47] B. Yu and M. P. Singh. Distributed reputation management for electronic commerce. Computational Intelligence, 18(4):535–549, 2002.
[48] L. Yu and B. F. Schmid. A conceptual framework for agent oriented and role based workflow modeling. In Proceedings of First International Workshop on Agent-Oriented Information Systems, pages 107–120, June 1999.
[49] G. Zacharia, A. Moukas, and P. Maes. Collaborative reputation mechanisms in electronic marketplaces. In Proceedings of the 32nd Annual Hawaii International Conference on Systems Sciences, 1999.
[50] F. Zambonelli, N. R. Jennings, and M. Wooldridge. Developing multiagent systems: the Gaia methodology. ACM Transactions on Software Engineering Methodology, 12(3):317–370, July 2003.