Multi-agent systems are subject to performance bottlenecks in cases where agents cannot perform tasks by themselves due to insufficient resources. Solutions to such problems include passing tasks to others or agent migration to remote hosts. We propose agent cloning as a more comprehensive approach to the problem of local agent overloads. According to our paradigm, agents may clone, pass tasks to others, die or merge.
Onn Shehory, Katia P. Sycara, Prasad Chalasani, So