The paper presents a framework called the contract net for distributed problem solving, where tasks are distributed through negotiation between nodes. It defines distributed problem solving as the cooperative solution of problems by a decentralized and loosely coupled collection of problem solvers. The contract net protocol specifies communication and control in a distributed problem solver, with task distribution viewed as an interactive process involving discussion between a node with a task and a group of nodes that may be able to execute the task. The discussion is the origin of the negotiation metaphor, where task distribution is viewed as a form of contract negotiation. The paper emphasizes that protocols for distributed problem solving should help determine the content of the information transmitted, rather than simply provide a means of sending bits from one node to another. The use of the contract net framework is demonstrated in the solution of a simulated problem in area surveillance. The paper discusses the mode of operation of a distributed sensing system, a network of nodes extending throughout a relatively large geographic area, whose primary aim is the formation of a dynamic map of traffic in the area. From the results of this preliminary study, the paper abstracts features of the framework applicable to problem solving in general, examining in particular transfer of control. Comparisons with PLANNER, CONNIVER, HEARSAY-II, and PUP6 are used to demonstrate that negotiation -- the two-way transfer of information -- is a natural extension to the transfer of control mechanisms used in earlier problem-solving systems. The paper also discusses the importance of negotiation as a fundamental mechanism for interaction in distributed problem solving. It describes the contract net protocol, which provides a set of message types that indicate the kind of information that nodes should exchange in order to effect one form of cooperation. The paper also discusses the importance of negotiation in the context of transfer of control and as a way of viewing invocation as the matching of KSs to tasks. The paper concludes that negotiation is a natural extension to the transfer of control mechanisms used in earlier problem-solving systems.The paper presents a framework called the contract net for distributed problem solving, where tasks are distributed through negotiation between nodes. It defines distributed problem solving as the cooperative solution of problems by a decentralized and loosely coupled collection of problem solvers. The contract net protocol specifies communication and control in a distributed problem solver, with task distribution viewed as an interactive process involving discussion between a node with a task and a group of nodes that may be able to execute the task. The discussion is the origin of the negotiation metaphor, where task distribution is viewed as a form of contract negotiation. The paper emphasizes that protocols for distributed problem solving should help determine the content of the information transmitted, rather than simply provide a means of sending bits from one node to another. The use of the contract net framework is demonstrated in the solution of a simulated problem in area surveillance. The paper discusses the mode of operation of a distributed sensing system, a network of nodes extending throughout a relatively large geographic area, whose primary aim is the formation of a dynamic map of traffic in the area. From the results of this preliminary study, the paper abstracts features of the framework applicable to problem solving in general, examining in particular transfer of control. Comparisons with PLANNER, CONNIVER, HEARSAY-II, and PUP6 are used to demonstrate that negotiation -- the two-way transfer of information -- is a natural extension to the transfer of control mechanisms used in earlier problem-solving systems. The paper also discusses the importance of negotiation as a fundamental mechanism for interaction in distributed problem solving. It describes the contract net protocol, which provides a set of message types that indicate the kind of information that nodes should exchange in order to effect one form of cooperation. The paper also discusses the importance of negotiation in the context of transfer of control and as a way of viewing invocation as the matching of KSs to tasks. The paper concludes that negotiation is a natural extension to the transfer of control mechanisms used in earlier problem-solving systems.