Abstract. Unlike monotone single-valued functions, multivalued mappings may have zero, one, or (possibly infinitely) many minimal fixed-points. The contribution of this work is twofold. First, we overview and investigate the existence and computation of minimal fixed-points of multivalued mappings, whose domain is a complete lattice and whose range is its power set. Second, we show how these results are applied to a general form of logic programs, where the truth space is a complete lattice. We show that a multivalued operator can be defined whose fixed-points are in one-to-one correspondence with the models of the logic program. The topic of this work is the overview and investigation of the fixed-points of multivalued functions f : L → 2 L (multivalued functions are also called correspondences, or set-valued functions, in the literature). Such functions naturally arise, e.g., in the specification of the semantics of nondeterministic programming languages [7,8,11,18,31,36,37,44], in game theory [6,33,45,53], and in disjunctive logic programming [22,27,32,42,52]; those of the latter case motivated our work. Informally, (i) in the first case, the meaning of a nondeterministic 1 program P may be seen as a function p : S → 2 S , where S is the set of states a program may assume. The image of p is a finite nonempty set, as at a given step of a program execution, due to a nondeterministic statement, more than one successive state is possible. The semantics of a program is then related to the fixed-points of such functions (s ∈ p(s)); (ii) in the second case, a game is represented as a function g : S → 2 S , where S is the strategy space of the involved players, and fixed-points (s ∈ g(s)) are related to the so-called Nash equilibria of the game. The image of g is a nonempty (usually finite) set, as at each step of the game, more than one incomparable strategic choice is possible; and