Resumen
The article argues that the agent-based computing provides important advantages for scientific computing. It provides ideas in the context of a particular application, the simulation of gas turbine engines. This application is typical in that it involves an enormously complex device of great economic importance, one whose design is continually evolving to achieve higher value and to fit new uses. In the implementation, the recommender agents help select the algorithm and its executable implementation. The connection between the PYTHIA system, providing recommender agents, and GAMS, a mathematical software, is achieved by a proxy software program that is configured for this purpose. The proxy serves to enforce acceptability criteria on the user's input. While PYTHIA supplies the recommender agents that interface with GAMS, the solver and mediator agents are provided by the SciAgents system. SciAgents provides a robust mechanism for cooperation among the computing agents. The multiagent architecture presented here enables to combine existing full-fledged problem-solving environments. INSET: Tools Available for Scientific Computing.