A Software Framework for Automated Negotiation

Abstract

Abstract. If agents are to negotiate automatically with one another they must share a negotiation mechanism, specifying what possible actions each party can take at any given time, when negotiation terminates, and what is the structure of the resulting agreements. Current standardization activities such as FIPA [2] and WS-Agreement [3] represent this as a negotiation protocol specifying the flow of messages. However, they omit other aspects of the rules of negotiation (such as obliging a participant to improve on a previous offer), requiring these to be represented implicitly in an agent's design, potentially resulting incompatibility, maintenance and re-usability problems. In this chapter, we propose an alternative approach, allowing all of a mechanism to be formal and explicit. We present (i) a taxonomy of declarative rules which can be used to capture a wide variety of negotiation mechanisms in a principled and well-structured way; (ii) a simple interaction protocol, which is able to support any mechanism which can be captured using the declarative rules; (iii) a software framework for negotiation that allows agents to effectively participate in negotiations defined using our rule taxonomy and protocol and (iv) a language for expressing aspects of the negotiation based on OWL-Lite [4]. We provide examples of some of the mechanisms that the framework can support.

SOLACE: A Framework for Electronic Negotiations

“…Recent software frameworks for the design and implementation of e-negotiation media and support tools include SMACE (Cardoso & Oliveira, 2000), DynamiCS (Tu et al, 2001), INSULA (Benyoucef et al, 2001), SILKROAD (Strobel, 2001), MAP (Bichler et al, 2002), and Bartolini et al, 2002. In SILKROAD, Strobel proposed a design and application framework for electronic negotiations.…”

“…Another group of researchers who have put forward an e-negotiation framework is Bartolini et al (2002). Accordingly, these authors designed a generic interaction protocol and a general interaction framework using the same protocol, which can be parameterized with different negotiations.…”

“…As can be seen above, most existing frameworks (Cardoso & Oliveira, 2000;Tu et al, 2001;Bichler et al, 2002) are suited to the particular needs of the system at hand and cannot be applied across the board in other scenarios. On the other hand, the frameworks by Strobel, (2001) and Bartolini et al, (2002) fulfill many functions of an e-negotiation platform.…”

“…Research into electronic negotiations has provided a variety of fully automated and semi-automated negotiation systems employing the use of agents, decision support systems, and negotiation support systems (Zlatev & Van Eck, 2003). Nevertheless, the general frameworks for automated negotiation that have been proposed in the past few years (Wong et al, 2000, Jennings et al, 2001Bartolini et al, 2002) do not pay attention to these differences, making it difficult to assess which is the most applicable in a specific negotiation domain. Most negotiation systems are based on different frameworks and models, with each researcher developing a framework for their own system.…”

“…Most negotiation systems are based on different frameworks and models, with each researcher developing a framework for their own system. A few attempts (Strobel, 2001;Bartolini et al, 2002) have been made at developing generic frameworks or models, but more research still has to be carried out in developing electronic negotiation frameworks to create more robust and standardized frameworks. This approach will prove very beneficial to all parties in this field of research by providing a standard on which future works in electronic negotiation support can be based.…”