A two-level negotiation framework for complex negotiations

2009

With an increasing number of applications in the context of multi-agent systems, automated negotiation is a rapidly growing area. Written by top researchers in the field, this state-of-the-art treatment of the subject explores key issues involved in the design of negotiating agents, covering strategic, heuristic, and axiomatic approaches. The authors discuss the potential benefits of automated negotiation as well as the unique challenges it poses for computer scientists and for researchers in artificial intelligence. They also consider possible applications and give readers a feel for the types of domain where automated negotiation is already being deployed. This book is ideal for graduate students and researchers in computer science who are interested in multi-agent systems. It will also appeal to negotiation researchers from disciplines such as management and business studies, psychology, and economics.

Proceeding

The increasing demand for distributed entities to interact in complex domains necessitates the need for cooperation, coordination and negotiation to reach agreement. Examples of such systems are: the flow of work and information through cooperating companies (virtual enterprises), international air traffic controllers, the coordination of logistic processes in shipping companies, the use of flexible transport systems in industrial manufacturing and assembly, and the operation of multi-guidance and control systems. This paper describes the design of a model that uses a hierarchy of negotiation protocols to solve conflicts in any of the INTERRAP layers. Two testbeds have been developed to test the proposed hierarchical model: a Desktop Configuration and a Travel Planning Domains. The testbeds proved the effectivness of the model in solving conflicts among several agents in all the INTERRAP layers. These two domains have been chosen because they introduce various types of conflictswhich could be solved using various negotiation protocols in the model.

Engineering Applications of Artificial Intelligence, 2013

An agent-based negotiation team is a group of interdependent agents that join together as a single negotiation party due to their shared interests in the negotiation at hand. The reasons to employ an agent-based negotiation team may vary: (i) more computation and parallelization capabilities; (ii) unite agents with different expertise and skills whose joint work makes it possible to tackle complex negotiation domains; (iii) the necessity to represent different stakeholders or different preferences in the same party (e.g., organizations, countries, married couple, etc.). The topic of agent-based negotiation teams has been recently introduced in multi-agent research. Therefore, it is necessary to identify good practices, challenges, and related research that may help in advancing the state-of-the-art in agent-based negotiation teams. For that reason, in this article we review the tasks to be carried out by agent-based negotiation teams. Each task is analyzed and related with current advances in different research areas. The analysis aims to identify special challenges that may arise due to the particularities of agent-based negotiation teams.

2002

Structured negotiation is proposed as a new method through which collaborating agents can seek consensus on the apportionment of tasks and resources. The approach draws on research in collaborative planning and human dialog understanding: agent i n teractions are organized in a manner that re ects the structure of a shared plan. Negotiations are incremental and interleaved with the shared planning process while communications supporting negotiations are made e cient b y d r a wing on knowledge of a prevailing context. Agent proposals to team members are annotated with causal information that compactly expresses relationships between new proposals and the current c o n text. Normative guidelines for proposal generation further restrict communications of ancillary information to only those fragments that represent departures from the norm. Finally, a set of interpretation rules allows agents to infer information not explicitly communicated. Categories and Subject Descriptors I.2.11 Computing Methodologies]: Arti cial Intelligence|

Current and Future Developments in Artificial Intelligence, 2017

In the past few years, there is a growing interest in automated negotiation in which software agents facilitate negotiation on behalf of their users and try to reach joint agreements. The potential value of developing such mechanisms becomes enormous when negotiation domain is too complex for humans to find agreements (e.g. e-commerce) and when software components need to reach agreements to work together (e.g. web-service composition). Here, one of the major challenges is to design agents that are able to deal with incomplete information about their opponents in negotiation as well as to effectively negotiate on their users' behalves. To facilitate the research in this field, an automated negotiating agent competition has been organized yearly. This paper introduces the research challenges in ANAC 2014 and explains the competition set up and competition results. Furthermore, a detailed analysis of the best performing five agent has been examined.

Knowledge …, 1999

Lecture Notes in Business Information Processing, 2014

We present an architecture that makes use of symbolic decision-making to support agents participating in concurrent bilateral negotiations. The architecture is a revised version of previous work with the KGP model , which we specialise with knowledge about the agent's self, the negotiation opponents and the environment. Our work combines the specification of domain-independent decision-making with a new protocol for concurrent negotiation that revisits the well-known alternating offers protocol . We show how the decision-making can be specialised to represent the agent's strategies, utilities and preferences using a Prolog-like meta-program. The work prepares the ground for supporting decision-making in concurrent bilateral negotiations that is more lightweight than previous work and contributes towards a fully developed model of the architecture.

2000

Negotiation …, 2008

In fully automated e-negotiation all involved parties are software agents, so negotiation takes place in a multiagent system between software agents that have been developed as a computer system for automating tasks in a specific application domain. A multiagent system is a ...

2009

Electronic business negotiations are enabled by different electronic negotiation models: automated negotiation models for software agents, negotiation support models for human negotiators, and auction models for both. To date, there is no electronic negotiation model that enables bilateral multi-issue negotiations between a human negotiator and a negotiation agent-an important task in electronic negotiation research. In this thesis, a model is presented that integrates the automated negotiation model and the negotiation support model. The resulting hybrid negotiation model paves the way for human-agent business negotiations. The integration of two models is realised at the levels of negotiation process, communication support and decision making. To this end, the negotiation design, negotiation process, negotiation decision making, and negotiation communication in negotiation support systems (NSSs) and agent negotiation systems (ANSs) are studied and analysed. The analyses on these points help in strengthening the motivation behind hybrid negotiation model and setting aims for the integration of an NSS and an ANS in hybrid negotiation model. We mainly propose a human-agent negotiation design, negotiation process protocols to support the design, a hybrid communication model for human-agent interaction, an agent decision-making model for negotiation with human, and a component for interoperability between NSS and ANS. The agent decision-making model is composed of heuristic and argumentationbased negotiation techniques. It is proposed after analysing different automated negotiation models for different human negotiation strategies. The proposed communication model supports human negotiator and negotiation agent to understand and process negotiation messages from each other. This communication model consists of negotiation ontology, a wrapper agent, and a proper selection of an agent communication language (ACL) and a content language. The wrapper agent plays a role for interoperability between agent system and NSS by providing a communication interface along with the negotiation ontology. The negotiation ontology, ACL and agent content language make the communication model of negotiation agent in ANS. The proposed hybrid model is realised by integrating an ANS into NSS Negoisst. The research aim is to 1.2.2 Hybrid Communication Model and Agent Communication Model Communication is an essential part of a negotiation process and it is about exchanging negotiation messages between negotiators. With a hybrid (human-agent) communication model for human-agent negotiation, our aim is to bridge the gap between the communication models of Negoisst and ANS in order to enable two different communicatory entities to communicate their negotiation stance to each other. A communication model in any negotiation system normally defines the structure of negotiation messages and the representation and semantics of contents in messages. The hybrid communication model must thus be based on a thorough analysis of the negotiation communication behaviour and the structure of negotiation messages in NSSs and ANSs. A communication behaviour in a negotiation message can be represented through an offer containing negotiation issues' values with or without text representing the arguments, queries about product or service, clarifications about some negotiation matter, greetings etc. The structure of a negotiation message in NSSs and ANSs is