To make the agents negotiate more efficiently in bilateral multi-issue negotiation in multi-agent based competitive e-commerce

an agent negotiation model in competitive environment is presented

and the Improved Genetic Algorithm (IGA) is applied in the model to enhance the negotiation efficiency. After 1000 times of experiments for the four kinds of agents in the same condition

the Standard Genetic Algorithm (SGA) averagely needs negotiation of 360 runs

Genetic Algorithm based on Metropolis rule (MGA) averagely needs 230 runs

Adaptive Genetic Algorithm AGA averagely needs 207 runs

while the IGA averagely needs only 151 runs. The experiment results show that the IGA can gain the optimal negotiation result more efficiently than other three kinds of genetic algorithms in competitive bilateral multi-issue negotiation.