We address the issue, in cognitive agents, of possible loss of previous information, which later might turn out to be correct when new information becomes available. To this aim, we propose a framework for changing the agent's mind without erasing forever previous information, thus allowing its recovery in case the change turns out to be wrong. In this new framework, a piece of information is represented as an argument which can be more or less accepted depending on the trustworthiness of the agent who proposes it. We adopt possibility theory to represent uncertainty about the information, and to model the fact that information sources can be only partially trusted. The originality of the proposed framework lies in the following two points: (i) argument reinstatement is mirrored in belief reinstatement in order to avoid the loss of previous information; (ii) new incoming information is represented under the form of arguments and it is associated with a plausibility degree depending on the trustworthiness of the information source.

We consider a framework for preference aggregation on multiple binary issues, where agents' preferences are represented by (possibly cyclic) CP-nets. We focus on the majority aggregation of the individual CP-nets, which is the CP-net where the direction of each edge of the hypercube is decided according to the majority rule. First we focus on hypercube Condorcet winners (HCWs); in particular, we show that, assuming a uniform distribution for the CP-nets, the probability that there exists at least one HCW is at least 1-1/e, and the expected number of HCWs is 1. Our experimental results confirm these results. We also show experimental results under the Impartial Culture assumption. We then generalize a few tournament solutions to select winners from (weighted) majoritarian CP-nets, namely Copeland, maximin, and Kemeny. For each of these, we address some social choice theoretic and computational issues.

The social lending market, with over a billion dollars in loans, is a two-sided matching market where borrowers specify demands and lenders specify total budgets and their desired interest rates from each acceptable borrower. Because different borrowers correspond to different risk-return profiles, lenders have preferences over acceptable borrowers; a borrower prefers lenders in order of the interest rates they offer to her. We investigate the question of what is a computationally feasible, 'good', allocation to clear this market. We design a strongly polynomial time algorithm for computing a Pareto-efficient stable outcome in a two-sided many-to-many matching market within differences, and use this to compute an allocation for the social lending market that satisfies the properties of stability — a standard notion of fairness in two-sided matching markets — and Pareto efficiency; and additionally addresses envy-freeness amongst similar borrowers and risk diversification for lenders.

Gjerstad and Dickhaut, 1998; Nicolaisen et al., 2001] and a market selection strategy which is mainly based on the history This paper describes the strategies used by of the trader's profit made with each specialist. AstonCAT-Plus, the post-tournament version of A CAT game lasts a number of days (500 days in CATthe specialist designed for the TAC Market Design 2010). Each day consists of a number of trading rounds, Tournament 2010. It details how AstonCATwhich each lasts for a known constant length of time. The Plus accepts shouts, clears market, sets transaction daily evaluation of the specialists is based on three metrics: prices and charges fees. Through empirical evaluation, (1) market share, which is the percentage of the total traders' we show that AstonCAT-Plus not only outperforms population registered in the market; (2) profit share, which is AstonCAT (tournament version) significantly the ratio of the daily profit a specialist obtains to the profit of but also achieves the second best overall all specialists and (3) transaction success rate (TSR), which score against some top entrants of the competition.

In this paper we propose a mechanism that encourages agents, participating in an open MAS, to follow a desirable behaviour, by introducing modifications in the environment. This mechanism is deployed by using an infrastructure based on institutional agents called incentivators. Each external agent is assigned to an incentivator that is able to discover its preferences, and to learn the suitable modifications in the environment, in order to improve the global utility of a system in response to inadequate design or changes in the population of participating agents. The mechanism is evaluated in a p2p scenario.

There is a fundamental incompatibility between efficiency, interim individual rationality, and budget-balance in mechanism design, even for extremely simple settings. Yet it is possible to specify efficient mechanisms that satisfy participation and budget-balance constraints in expectation, prior to types being realized. We do so here, in fact deriving mechanisms that are individually rational for each agent even ex post of other agents' type realizations. However, participation must still bear some risk of loss. For agents that are risk neutral, we show how the center can extract the entire surplus in expectation, or alternatively provide an equal expected share of the surplus for each participant, without violating dominant strategy incentive compatibility, efficiency, or ex ante budget-balance. We compare these solutions to a third efficient mechanism we design explicitly to address risk aversion in trade settings: payments are defined to minimize the odds of loss, satisfying ex ante participation constraints for agents with attitudes toward risk ranging from neutrality to high loss-aversion.

Cake cutting is a playful name for the problem of fairly dividing a heterogeneous divisible good among a set of agents. The agent valuations for different pieces of cake are typically assumed to be additive. However, in certain practical settings this assumption is invalid because agents may not have positive value for arbitrarily small "crumbs" of cake. In this paper, we propose a new, more expressive model of agent valuations that captures this feature. We present an approximately proportional algorithm for any number of agents that have such expressive valuations. The algorithm is optimal in the sense that no other algorithm can guarantee a greater worst-case degree of proportionality. We also design an optimal approximately proportional and fully envy-free algorithm for two agents.

Given an argumentation framework and a group of agents, the individuals may have divergent opinions on the status of the arguments. If the group needsto reach a common position on the argumentation framework, the question is how the individual evaluations can be mapped into a collective one. Thisproblem has been recently investigated by Caminada and Pigozzi. In this paper, we investigate the behaviour of two of such operators from a socialchoice-theoretic point of view. In particular, we study under which conditions these operators are Pareto optimal and whether they are manipulable.

Trust is crucial in dynamic multi-agent systems, where agents may frequently join and leave, and the structure of the society may often change. In these environments, it may be difficult for agents to form stable trust relationships necessary for confident interactions. Societies may break down when trust between agents is too low to motivate interactions. In such settings, agents should make decisions about who to interact with, given their degree of trust in the available partners. We propose a decision-theoretic model of trust decision making allows controls to be used, as well as trust, to increase confidence in initial interactions. We consider explicit incentives, monitoring and reputation as examples of such controls. We evaluate our approach within a simulated, highly-dynamic multi-agent environment, and show how this model supports the making of delegation decisions when trust is low.

Alternating-time temporal logic (ATL) is a well-known logic for reasoning about strategic abilities of agents. An important feature that distinguishes variants of ATL for imperfect information scenarios is that the standard fixed point characterizations of temporal modalities do not hold anymore. In this paper, we show that adding explicit fixed point operators to the "next-time" fragment of ATL already allows to capture abilities that could not be expressed in ATL. We also illustrate that the new language allows to specify important kinds of abilities, namely ones where the agents can always recompute their strategy while executing it. Thus, the agents are not assumed to remember their strategy by definition, like in the existing variants of ATL. Last but not least, we show that verification of such abilities can be cheaper than for all the variants of `"ATL with imperfect information" considered so far.