Search

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in terms of processing power and time. In this paper, we investigate the feasibility of creating smaller, highly-performing specialized algorithms by way of fine-tuning. To do this, we first present a large pre-trained model with 20 unique scenarios that combine different social contexts with games of varying social dilemmas, record its answers, and use them for Q&A fine-tuning on a smaller model of the same family. Our focus is on in-context game-theoretic decision-making, the same domain within which human interaction occurs and that requires both a theory of mind (or a semblance thereof) and an understanding of social dynamics. The smaller model is therefore trained not just on the answers provided, but also on the motivations provided by the larger model, which should contain advice and guidelines to navigate both strategic dilemmas and social cues. We find that the fine-tuned smaller language model consistently bridged the gap in performance between the smaller pre-trained version of the model and its larger relative and that its improvements extended in areas and contexts beyond the ones provided in the training examples, including on out-of-sample scenarios that include completely different game structures. On average for all games, through fine-tuning, the smaller model showed a 46% improvement measured as alignment towards the behavior of the larger model, with 100% representing indistinguishable behavior. When presented with out-of-sample social contexts and games, the fine-tuned model still displays remarkable levels of alignment, reaching an improvement of 18% and 28% respectively., Comment: 18 pages, 6 figures

Within an increasingly digitalized organizational landscape, this research delves into the dynamics of decentralized collaboration, contrasting it with traditional collaboration models. An effective capturing of high-level collaborations (beyond direct massages) is introduced as the network construction methodology including both temporal and content dimensions of user collaborations - an Alternating Timed Interaction (ATI) metric as the first aspect, and a quantitative strategy of thematic similarity as the second aspect. This study validates three hypotheses that collectively underscore the complexities of digital team dynamics within sociotechnical systems: Firstly, it establishes the significant influence of problem context on team structures in work environments, emphasizing the need to consider the specific nature of tasks in analyzing collaborative dynamics. Secondly, the study reveals specific evolving patterns of team structures on digital platforms concerning team size and artifact maturity. Lastly, it identifies substantial differences in team structure patterns between digital platforms and traditional organizational settings, underscoring the unexplored nature of digital collaboration dynamics. The findings of this study are instrumental for organizations navigating the digital era, offering insights into effective knowledge sharing in the decentralized leadership of digital teams. By mapping out network structures and collaborative patterns, this study, with a focus on Wikipedia as a representative digital platform, paves the way for strategic interventions to optimize digital team dynamics and align them with broader organizational goals., Comment: 14 pages, 4 figures

This paper investigates the strategic decision-making capabilities of three Large Language Models (LLMs): GPT-3.5, GPT-4, and LLaMa-2, within the framework of game theory. Utilizing four canonical two-player games -- Prisoner's Dilemma, Stag Hunt, Snowdrift, and Prisoner's Delight -- we explore how these models navigate social dilemmas, situations where players can either cooperate for a collective benefit or defect for individual gain. Crucially, we extend our analysis to examine the role of contextual framing, such as diplomatic relations or casual friendships, in shaping the models' decisions. Our findings reveal a complex landscape: while GPT-3.5 is highly sensitive to contextual framing, it shows limited ability to engage in abstract strategic reasoning. Both GPT-4 and LLaMa-2 adjust their strategies based on game structure and context, but LLaMa-2 exhibits a more nuanced understanding of the games' underlying mechanics. These results highlight the current limitations and varied proficiencies of LLMs in strategic decision-making, cautioning against their unqualified use in tasks requiring complex strategic reasoning., Comment: 25 pages, 12 figures

This paper introduces a new scheme for autonomous electricity cooperatives, called predictive cooperative (PCP), which aggregates commercial and residential electricity consumers and participates in the electricity market on behalf of its members. An axiomatic approach is proposed to calculate the day-ahead bid and to disaggregate the collective cost among participating consumers. The resulting formulation is shown to keep the members incentivized to both participate in the cooperative and remain truthful in reporting their expected loads. The scheme is implemented using PJM (world's largest wholesale electricity market) real-time and day-ahead price data for 2015 and a collection of residential and commercial load profiles. The model performance of this framework is compared to that of real-time pricing (RTP) scheme, in which wholesale market prices are directly applied to individual consumers. The results show truthful load announcement by consumers, reduction in electricity price variation for all consumers, and comparative benefits for participants., Comment: 9 pages

Distributed architectures have become ubiquitous in many complex technical and socio-technical systems because of their role in improving uncertainty management, accommodating multiple stakeholders, and increasing scalability and evolvability. This departure from monolithic architectures provides a system with more flexibility and robustness in response to uncertainties that it may confront during its lifetime. Distributed architecture does not provide benefits only, as it can increase cost and complexity of the system and result in potential instabilities. The mechanisms behind this trade-off, however, are analogous to those of the widely-studied transition from integrated to modular architectures. In this paper, we use a conceptual decision framework that unifies modularity and distributed architecture on a five-stage systems architecture spectrum. We add an extensive computational layer to the framework and explain how this can enhance decision making about the level of modularity of the architecture. We then apply it to a simplified demonstration of the Defense Advanced Research Projects Agency (DARPA) fractionated satellite program. Through simulation, we calculate the net value that is gained (or lost) by migrating from a monolithic architecture to a distributed architecture and show how this value changes as a function of uncertainties in the environment and various system parameters. Additionally, we use Value at Risk as a measure for the risk of losing the value of distributed architecture, given its inherent uncertainty., Comment: 12 pages

This paper introduces a conceptual, yet quantifiable, architecture framework by extending the notion of system modularity in its broadest sense. Acknowledging that modularity is not a binary feature and comes in various types and levels, the proposed framework introduces higher levels of modularity that naturally incorporate decentralized architecture on the one hand and autonomy in agents and subsystems on the other. This makes the framework suitable for modularity decisions in Systems of Systems and for analyzing the impact of modularity on broader surrounding ecosystems. The stages of modularity in the proposed framework are naturally aligned with the level of variations and uncertainty in the system and its environment, a relationship that is central to the benefits of modularity. The conceptual framework is complemented with a decision layer that makes it suitable to be used as a computational architecture decision tool to determine the appropriate stage and level of modularity of a system, for a given profile of variations and uncertainties in its environment. We further argue that the fundamental systemic driving forces and trade-offs of moving from monolithic to distributed architecture are essentially similar to those for moving from integral to modular architectures. The spectrum, in conjunction with the decision layer, could guide system architects when selecting appropriate parameters and building a system-specific computational tool from a combination of existing tools and techniques. To demonstrate the applicability of the framework, a case for fractionated satellite systems based on a simplified demo of the DARPA F6 program is presented., Comment: 22 pages

This paper introduces a framework for studying the interactions of autonomous system components and the design of the connectivity structure in Systems of Systems (SoSs). This framework, which uses complex network models, is also used to study the connectivity structure's impact on resource management. We discuss resource sharing as a mechanism that adds a level of flexibility to distributed systems and describe the connectivity structures that enhance components' access to the resources available within the system. The framework introduced in this paper explicitly incorporates costs of connection and the benefits that are received by direct and indirect access to resources and provides measures of the optimality of connectivity structures. We discuss central and a distributed schemes that, respectively, represent systems in which a central planner determines the connectivity structure and systems in which distributed components are allowed to add and sever connections to improve their own resource access. Furthermore, we identify optimal connectivity structures for systems with various heterogeneity conditions., Comment: 19 pages. To appear in Systems Engineering Journal 2016

We introduce a heterogeneous connection model for network formation to capture the effect of cost heterogeneity on the structure of efficient networks. In the proposed model, connection costs are assumed to be separable, which means the total connection cost for each agent is uniquely proportional to its degree. For these sets of networks, we provide the analytical solution for the efficient network and discuss stability impli- cations. We show that the efficient network exhibits a core-periphery structure, and for a given density, we find a lower bound for clustering coefficient of the efficient network., Comment: 9 pages