The purpose of this article is optimising maximum power output (MPO) and minimum entropy generation (MEG) of an Atkinson cycle as a multi-objective constraint thermodynamic problem by a new improved artificial bee colony algorithm which utilises 'mutable smart bee' (MSB) instead of conventional bees. The results have been checked with some of the most common optimising algorithms like Karaboga's original artificial bee colony, bees algorithm (BA), improved particle swarm optimisation (IPSO), Lukasik firefly algorithm (LFFA) and self-adaptive penalty function genetic algorithm (SAPF-GA). Mutable smart bee (MSB) is able to maintain its historical memories for the location and quality of food sources and also a little chance of mutation during the searching process is considered for this bee. These features were found as strong elements for mining data in constraint areas and the results will prove this claim.