Abstract-Agent-based technology has generated a lot of attention in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. So me problems in real world cannot be handled by a single agent. Mult iple agents work together to accomplish some task. A lthough mu lti-agent systems (MASs) provide many potential advantages, they also present many difficult challenges. This paper illustrates the importance of communication for planning in a mult i-agent setting by considering a grid wo rld do main that consists of obstacles at different locations. This paper provides a theoretical framework that is validated by the experimental results. Performance analysis with respect to plan size and execution time is also reported.