Social Trust: A Cognitive Approach Cristiano Castelfranchi and Rino Falcone National Research Council - Institute of Psychology * Unit of "AI, Cognitive Modelling and Interaction" Roma - Italy Abstract After arguing about the crucial importance of trust for Agents and MAS, we provide a definition of trust both as a mental state and as a social attitude and relation. We present the mental ingredients of trust: its specific beliefs and goals, with special attention to evaluations and expectations. We show the relation between trust and the mental background of delegation. We explain why trust is a bet, and implies some risks, and analyse the more complex forms of social trust, based on a theory of mind and in particular on morality, reputation and disposition, and authority (three party trust). We explain why promises, contracts, authorities can increase our trust by modifying our mental representations. We present a principled quantification of trust, based on its cognitive ingredients, and use this "degree of trust" as the basis for a rational decision to delegate or not to another agent. We explain when trust is rational, and why it is not an irrational decision by definition. We also criticise the economic and game-theoretic view of trust for underestimating the importance of cognitive ingredients of trust and for reducing it to subjective probability and risk. The paper is intended to contribute both to the conceptual analysis and to the practical use of trust in social theory and MAS. 1. Premise: the importance of trust As it has been written in the call of the original workshop “In recent research on electronic commerce trust has been recognized as one of the key factors for successful electronic commerce adoption. In electronic commerce problems of trust are magnified, because agents reach out far beyond their familiar trade environments. Also it is far from obvious whether existing paper-based techniques for fraud detection and prevention are adequate to establish trust in an electronic network environment where you usually never meet your trade partner face to face, and where messages can be read or copied a million times without leaving any trace. (..) With the growing impact of electronic commerce distance trust building becomes more and more important, and better models of trust and deception are needed. One trend is that in electronic communication channels extra agents, the so-called Trusted Third Parties, are introduced in an agent community that take care of trust building among the other agents in the network. But in fact different kind of trust are needed and should be modelled and supported: - trust in the environment and in the infrastructure (the socio-technical system); - trust in your agent and in mediating agents; - trust in the potential partners; - trust in the warrantors and authorities (if any). The notion of trust is also important in other domains of agents' theory, beyond that of electronic commerce. It seems even foundational for the notion of "agency" and for its defining relation of acting "on behalf of" [Cas2]. For example, trust is relevant in Human-Computer interaction, e.g., the trust relation between the user and her/his personal assistant (and, in general, her/his computer). It is also critical for modelling and supporting groups and teams, organisations, co-ordination, negotiation, with the related trade-off between local/individual utility and global/collective interest; or in modelling distributed knowledge and its circulation. In sum, the notion of trust is crucial for all the major topics of Multi-Agent systems. What is needed is a general and principled theory of trust, of its cognitive and affective components, and of its social functions. A theory has to be developed to answer questions like the following: When is trust rational? When is it over- confidence and risky? When is trust too weak and when do we waste time on redundant control * This research has been developed within the agreement between CNR and Provincia Autonoma di Trento, research project on “Applicazioni avanzate di informatica“. We would like to thanks Maria Miceli, YaoHua Tan, Maj Bonniver Tuomela, Giovan Francesco Lanzara, and Walter Thoen for useful comments and discussions.