Agent Execution Research Articles

Human-AI collaboration: Unraveling the effects of user proficiency and AI agent capability in intelligent decision support systems

Artificial intelligence (AI) agents are integral components of modern intelligent decision support systems (IDSS), providing their capability to assist in decision-making processes. Understanding the influence of AI involvement on human responses within these systems is crucial for fostering appropriate reliance on AI advice and ensuring a comfortable user experience. This study delves into the impact of AI agents on decision change, correct rate change, confidence rate change and pleasure rating among users. It explores the main and interactive effects of user proficiency and AI agent capability on user responses. A block-factorial experiment involving 45 participants was conducted. The results indicated that high-capability AI agents were associated with substantial decision change, correct rate change and confidence rate change. Participants with higher proficiency, both subjectively and objectively, exhibited reduced reliance on AI agents for task execution. Notably, the involvement of AI agents led to a slight decline in correct rates for participants of high competence (i.e., participants' independent correct rate exceeds AI agent capability), while still enhancing their confidence levels. Additionally, agents lacking human-like embodiment tended to enhance participants’ pleasure ratings. Individual differences in gender, collaboration experience with AI agent, and stereotype on AI agent capability also shaped the decision changes and pleasure ratings of participants. These findings underscore the presence of complementary competence interaction between user and AI agent within IDSS, and can be applied in designing capability of advisory AI agents with consideration of user proficiency and individual characteristics. Relevance to industryThe findings can be used as guidelines for designing AI agents and specifying their application strategies to integrate the assistance of AI agents effectively in intelligent decision support systems.

Game-theoretic distributed approach for heterogeneous-cost task allocation with budget constraints

This paper investigates heterogeneous-cost task allocation with budget constraints (HCTAB), wherein heterogeneity is manifested through the varying capabilities and costs associated with different agents for task execution. In contrast with the centralized optimization-based method, the HCTAB problem is solved using a fully distributed framework, and a coalition formation game is introduced to provide a theoretical guarantee for this distributed framework. To solve the coalition formation game, a convergence-guaranteed log-linear learning algorithm based on heterogeneous cost is proposed. This algorithm incorporates two improvement strategies, namely a cooperative exchange strategy and a heterogeneous-cost log-linear learning strategy. These strategies are specifically designed to be compatible with the heterogeneous cost and budget constraints characteristic of the HCTAB problem. Through ablation experiments, we demonstrate the effectiveness of these two improvements. Finally, numerical results show that the proposed algorithm outperforms existing task allocation algorithms and learning algorithms in terms of solving the HCTAB problem.

Testing of Deep Reinforcement Learning Agents with Surrogate Models

Deep Reinforcement Learning (DRL) has received a lot of attention from the research community in recent years. As the technology moves away from game playing to practical contexts, such as autonomous vehicles and robotics, it is crucial to evaluate the quality of DRL agents. In this article, we propose a search-based approach to test such agents. Our approach, implemented in a tool called Indago , trains a classifier on failure and non-failure environment (i.e., pass) configurations resulting from the DRL training process. The classifier is used at testing time as a surrogate model for the DRL agent execution in the environment, predicting the extent to which a given environment configuration induces a failure of the DRL agent under test. The failure prediction acts as a fitness function, guiding the generation towards failure environment configurations, while saving computation time by deferring the execution of the DRL agent in the environment to those configurations that are more likely to expose failures. Experimental results show that our search-based approach finds 50% more failures of the DRL agent than state-of-the-art techniques. Moreover, such failures are, on average, 78% more diverse; similarly, the behaviors of the DRL agent induced by failure configurations are 74% more diverse.

Military health system auditory blast injury prevention standard

The Department of Defense (DoD) lacks a single medical standard for prevention of auditory blast injury, relying on the Service Branches to develop their own guidance. The DoD Executive Agent established the Blast Injury Prevention Standards Recommendation (BIPSR) process, led by the DoD Blast Injury Research Coordinating Office (BIRCO), to investigate the effects of blast injuries on warfighters. The BIPSR Process implementation of the Auditory Blast Injury Type illuminated characteristics, capabilities, and limitations of current capabilities to predict and prevent auditory injuries. The evaluation resulted in the recommendation of 8-h Equivalent Level (LAeq8hr) as the interim MHS Auditory Blast Injury Prevention Standard to serve as the cross-Service standard while the community performs additional research to fill critical knowledge gaps. BIRCO is working to formalize the Military Health System Auditory Blast Injury Prevention standard to support updates and coordination across DoD guidance including military design standards and health protection policies.

Vertical incremental housing in São Paulo. The case of Minha Casa Minha Vida – Entidades

Incremental housing allows people to gradually appropriate urban space for their own use. The question remains how housing incrementalism relates to planning strategies for densification and revitalisation within dense urban cores, which can generate socio-spatial exclusion. Vertical incremental housing may offer the benefit of integrating incrementalism in well serviced urban areas but faces challenges in terms of higher land costs, technical complexity and development risk. This article presents an analysis of vertical incremental housing within the framework of the Brazilian Minha Casa Minha Vida – Entidades (MCMV-E) programme. MCMV-E allows social organisations to act as executive agents of housing policy. Under the MCMV-E programme, social organisations control federal funds for transforming vacant real estate into housing for low-income households. Despite its quantitative and qualitative significance, MCMV-E has received limited assessment in the academic literature. Whereas the literature to date has dismissed the programme in terms of its socio-spatial consequences, this paper analysis offers a more nuanced reading, arguing that MCMV-E has allowed low-income residents to successfully acquire housing in central and well serviced locations.

Engineering a self-fueling and self-reported theranostic nanocatalyst for amplified cancer imaging and chemodynamic therapy

Chemodynamic therapy (CDT) has sparked increasing interest in selective cancer treatment. However, it remains a challenge to achieve an efficient and sustained therapeutic effect due to the restricted Fenton chemistry and deficient catalytic substrates within the tumor microenvironment (TME). Meanwhile, the lack of strategies to timely monitor the delivery and execution of CDT agents increases the risks of unwanted side effects. Here, we present that integration of TME-triggered cascade catalysis with tumor metabolism reprogramming to engineer activatable theranostic nanocatalysts is an effective way to tackle these challenges. A self-fueling and self-reported theranostic nanocatalyst is reported in this study by modifying multi-enzyme mimic MnO2 nanosturctures with antisense oligonucleotides (ASO). This catalyst can produce free radicals through logic multi-enzymatic catalysis to induce oxidative damage to cancer cells, yet keeping inert in normal cells. Furthermore, the loaded ASO can silence MCT4 that overexpresses in tumor cells, resulting in efflux blockage of intracellular lactate and decrease of intracellular pH, which remarkably facilitates the cascade catalysis for amplified CDT. Meanwhile, such acidification triggers an MRI enhancement for reporting gene silencing. Results from in vivo testing further support the potential of our design for more effective CDT. This study offers different insights into the design and construction of advanced platforms for noninvasive imaging-guided treatment of a wide range of cancers.

A five-year case study analysis of USAID local governance programming and public investment spending in post-earthquake Haiti

In the aftermath of the 2010 Haiti earthquake, the central government operations were paralyzed, and municipal officials became even more important as they were more readily able to respond to their constituents’ needs during this time of crisis. The United States Agency for International Development’s (USAID) five-year post-earthquake Limyè ak Òganizasyon pou Kolektivite yo Ale Lwen (LOKAL+) program aimed to bolster the capacity of municipalities – beyond this disaster event – through revenue mobilization activities, within quake-affected and non-quake affected areas. The intended outcome of this effort was to improve local public service delivery throughout Haiti.Nearly all participating LOKAL+ municipalities experienced increased local revenue collection, particularly in property and business taxes, from 2012 through 2017. However, the impact of these increases on public investment spending was not evident even though this was a stated objective of the program. To evaluate whether public services improved in two of the nine LOKAL+ localities, due to USAID’s local revenue mobilization efforts, I employed a case study analysis using descriptive statistics, in-depth interviewing, and content analysis.The findings revealed modest public service improvements in one of the two case study sites. However, the political climate within which LOKAL+ was executed – mainly, the unlawful installation of interim executive agents throughout the country at the time – had an observed impact on the study’s findings. The implications of country-specific political economic realities on the timing of donor-led local governance efforts are underscored, as Haiti continues to navigate compounding political crises – including the assassination of the President in 2021 – since the end of the LOKAL+ program.

A simple learning agent interacting with an agent-based market model

We consider the learning dynamics of a single reinforcement learning optimal execution trading agent when it interacts with an event-driven agent-based financial market model. Trading takes place asynchronously through a matching engine in event time. The optimal execution agent is considered at different levels of initial order sizes and differently sized state spaces. The resulting impact on the agent-based model and market is considered using a calibration approach that explores changes in the empirical stylised facts and price impact curves. Convergence, volume trajectory and action trace plots are used to visualise the learning dynamics. The smaller state space agents had the number of states they visited converge much faster than the larger state space agents, and they were able to start learning to trade intuitively using the spread and volume states. We find that the moments of the model are robust to the impact of the learning agents, except for the Hurst exponent, which was lowered by the introduction of strategic order-splitting. The introduction of the learning agent preserves the shape of the price impact curves but can reduce the trade-sign auto-correlations and increase the micro-price volatility when the trading volumes increase.

Secure Mobile Agent Migration Using Lagrange Interpolation and Fast Fourier Transformation

Mobile agent is a processing unit works on the behalf of host computer. Mobile agent with intelligence provides a new computing prototype that is totally different from conventional prototype. Mobile agents are automatically itinerating from one host Computer to another host computer and execute assigned task on the behalf of user in heterogeneous environment under own control. Because mobile agents roam around distributed networks automatically, the security of the agents and platforms is a major concern. The number of mobile agents-based software applications has increased dramatically over the past year. It has also enhanced the security risks associated with such applications. Most protection systems in the mobile agent paradigm focus on platform security and provide few guidelines for mobile agent security, which is still a challenging topic. There is a risk to information carries by mobile agents from the malicious mobile agents who can modify and steal the confidential information. In this paper proposed multilevel authentication framework of mobile agents and platform based on Lagrange interpolation and fast Fourier transformation (LIFFT). In this frame work ‘n’ number of mobile agent have two level of security first level key used authentication and second level of key used for execution of mobile agents.

A Secured Multi Agent Architecture for Grid Computing

Grid computing provides big possibilities like resource sharing, resource virtualization, and capacity planning since diverse resources that are geographically dispersed are virtualized as a single entity. The associated security concerns are one of the key obstacles preventing grid computing from being broadly adopted and used. Users in a grid are concerned about the security of their assets and the privacy of their data. A host's security in terms of its data or virtual servers may be jeopardised when it interacts with a grid. By providing multilateral security, i.e., security for both the Grid client and the Grid supplier, our building design expands the degree of assurance that can be placed on the accuracy of a Grid calculation and the assurance of client-provided resources. We discuss the issue of ensuring security and present the multi-agent security construction analysis. The paper outlines a multi-agent strategy for protecting the grid environment's resources. The strategy is put forth to address the grid computing industry's growing, serious security issue. The paper defines a multi-agent security architecture that integrates the capabilities of agents with the Grid Security Infrastructure's basic security mechanism (GSI). A security Master agent and a few security task execution agents make up the strategy.

Family Hope Program Strategy in Improving the Welfare of the Mandalling Natal Community (Case Study: Social Service Mandalling Natal)

Education is the process of influencing learnes to adapt to the environment and can bring about changes in borth within and within the community. However, the scarcity of economics precludes schooling and even dropouts because they help families make ends meet. The study aims to know the implementation of policies and obstacles in the hope family program The study employs qualitative methods in which it is descriptive that give a clear picture of the problem at hand. Data collection techniques through interviews to informants who know information about the implementation of PKH policy, literature studies, observation, and documentation to support the results of the interview. The study shows tha the implementation of executive policy PKH has been seen from the few factors which are standard and target policy, human reseources and money reseources, executive agent PKH characteristics assist the recipient well, executive organization communication is well established, the social, economic, and political environment supports PKH. The study is based on the fact that the economic growth in the country will be affected mainly by education, with the existence of so- called debtors, it is possible to send their children to school even if there is a problem.

Development of smart energy systems for communities: technologies, policies and applications

The development of smart energy systems is a crucial enabler of the transition towards a decarbonized renewable energy (RE)-based society with universal energy access as it provides flexibility to integrate variable RE sources. This paper analyzes the development of new RE-based smart energy systems while introducing energy technologies and effective methods for energy systems development, recent progress of energy systems by using RE, practical government measures in pioneer countries for energy systems, development with quantitative data for these countries, and PEST (political, economic, socio-cultural and technological) analysis. Our findings show that the development of smart energy systems requires appropriate policies and that thorough collaboration between all national executive agents like national and local governments and citizens in this regard is crucial. Smart energy system development needs to be tailored to local conditions, and due consideration must be given new technologies and methods for development, correct policies, investment, collaboration national/local and their citizens, societal support, and citizens acceptance.

Implementasi Kebijakan Program Keluarga Harapan (PKH) di Bidang Pendidikan (Studi Kasus di Kelurahan Kota Matsum IV Kecamatan Medan Area)

Education is the process of influencing learnes to adapt to the environment and can bring about changes in borth within and within the community. However, the scarcity of economics precludes schooling and even dropouts because they help families make ends meet. The study aims to know the implementation of policies and obstacles in the hope family program in Matsum IV district Medan Area. The study employs qualitative methods in which it is descriptive that give a clear picture of the problem at hand. Data collection techniques through interviews to informants who know information about the implementation of PKH policy, literature studies, observation, and documentation to support the results of the interview. The study shows tha the implementation of executive policy PKH in Matsum IV, Medan Area has been seen from the few factors which are standard and target policy, human reseources and money reseources, executive agent PKH characteristics assist the recipient well, executive organization communication is well established, the social, economic, and political environment supports PKH. The study is based on the fact that the economic growth in the country will be affected mainly by education, with the existence of so- called debtors, it is possible to send their children to school even if there is a problem.

The Enduring Influence of Female Special Operations Executive Agent Biopics on Cultural Memory and Representations in France and Great Britain

Seventy-five years have elapsed since the end of World War Two. Yet, the memory of the conflict still occupies a central place in British and French collective consciousness. Fiction and film representations of the war act as powerful ‘vectors of memory’, to borrow an expression from French historian Henry Rousso, and as such, they have deeply contributed to shaping popular and cultural memories of the war.
 This article investigates a specific aspect of World War Two representations, namely the cinematic representations of the female agents from the SOE F section, focusing on the ‘generic’ or archetypal figure of the female SOE agent as generated by the post-war cultural industry. After a brief contextualisation focusing on Churchill’s clandestine organisation, the article will analyse the contribution of Odette (Herbert Wilcox, 1950) and Carve Her Name with Pride (Lewis Gilbert, 1958) to the construction of a World War Two ‘mythology’. It will then address more recent films, concentrating on Charlotte Gray (Gillian Armstrong, 2001) and Female Agents (Jean-Paul Salomé, 2008).
 How did the fictional construction of the female spy come to influence the social and cultural perception of the SOE agent? Are the tropes developed in such post-war films as Odette or Carve Her Name with Pride still current or have they evolved with time? The analysis of these fictional representations will reveal the permanence or evolution of certain representational patterns and also allow us to approach different perspectives on the cultural representation of World War Two on both sides of the Channel.

Measuring the Vulnerability of a Multi-Agent Pathfinding Solution

Multi-agent pathfinding is the problem of finding a non-interfering paths for a set of agents, such that if the agents follow these paths then each agent will reach its desired destination. Recent years have shown tremendous advances in this field, with optimal and suboptimal algorithms that are able to plan paths for over 100 agents in reasonable time. However, autonomous mobile agents are prime targets for cyber-security attacks, where an adversary may take control over an agent to disrupt the agents execution of their plan. This threat raises two questions. The first question is how much damage can an agent do if it does not follow its plan. The second question is how can one plan a-priori to be as robust as possible to such cyber-attacks. In this work, We provide an answer to both questions. To compute the maximal amount of damage that an adversary agent can do, we define a corresponding graph search problem and solve this problem with A*. Then, we provide a very simple method to choose a solution that is robust to such damages. We demonstrate both algorithms in simulation over standard multi-agent pathfinding domains.

Not too deep: Privacy, resistance, and the incorporation of social media in background checks

In May 2016, the United States Office of the Director of National Intelligence (ODNI) issued “Security Executive Agent Directive 5” (SEAD-5) (U.S. ODNI, 2016) authorizing the collection, use, and retention of social media information for the personnel security clearance process (PSCP), a process put in place to screen applicants for eligibility for national security and public trust positions. The incorporation of social media was a watershed moment for this process as social media, and even information from the entire Internet, had not been allowed into the investigation process before. The integration was not without resistance to the implementation, though, and backstage concerns about privacy emerged in Congressional hearings. What is most interesting to note, however, is that the resistance was for the most part in support of privacy for the potential employees of whom were receiving the check and the government’s obligations for the information collection; however, there was little, if any, mention of deeper, possibly problematic privacy concerns for the social media platforms and their mediated connections that co-create a second, derivative type of content beyond the access of their users. This paper examines the hearing “Incorporating social media into federal background investigations” in response to the SEAD-5 to see what the U.S. Congress did and did not discuss at the hearing and explores potential explanations for the inclusions/omissions, ultimately answering how those in charge of policies could have overlook deeper privacy complexities, and evaluating what this can mean for government, privacy, and policy researchers.

On the Evolution of Compositional Language

We present here a hierarchical model for the evolution of compositional language. The model has the structure of a two-sender/one-receiver Lewis signaling game augmented with executive agents who may learn to influence the behavior of the basic senders and receiver. The model shows how functional agents might coevolve representational roles even as they evolve a reliable compositional language in the context of costly signaling. When successful, the evolved language captures both the compositional structure of properties in the world and the compositional structure of successful actions involving those properties.

An improved energy management method based on combination of multi agent system and fuzzy logic

This paper presents a distributed energy management strategy based on a combination of multi agent system (MAS) and fuzzy logic (FL). Our system is composed of two renewable energy sources which are a photovoltaic panel, wind turbine, storage system and a variable loads. These elements are linked between them through switches. This improved technique allows the control of switches to manage the energy flow between sources and established load priority. MAS consider each element of the system as an agent, one of them is called execution agent that controls switches based on the paradigm of fuzzy logic (FL). The results of this approach are presented, discussed then followed by a simulation.

Composing Web Services Using a Multi-Agent Framework

Different web services can be composed to perform increasingly complex tasks (e.g., making an on-line payment). However, existing approaches compose web services with hard-coded control and data flows. To proactively and autonomously compose web services, developers can develop agents. However, the development of agents for service composition is complex, due to the reasons that: 1) developers may not have the knowledge from various domains to identify the necessary tasks to carry out the required web services; and 2) a deep understanding of the agent specific code is required in order to implement agents. To alleviate the required efforts to develop agents, we propose an approach to separate the development of agent specific code from the business logic code in the service composition. More specifically, we provide an easy-to-understand syntax that abstracts agent specific code and automatically generates executable agent code. Our experimental results show that our approach can accurately identify tasks for service composition with an Area Under the Curve (AUC) of 0.88. Our experiments also demonstrate that our approach can correctly generate agent code from seven agent specifications. Finally, our user studies reveal that developers are satisfied with our approach to develop agents for service composition.

Reformas que se parecen a sí mismas en el sistema penal juvenil uruguayo

(analítico) Se estudia el funcionamiento del sistema penal juvenil uruguayo a través de reiteradas modificaciones en la institucionalidad existente. Se trata de una investigación cualitativa de caso único, empírica y contextualizada, sustentada en el análisis de discurso de entrevistas a los agentes legislativos, judiciales y ejecutivos del sistema penal juvenil y de los documentos que figuran en una muestra de expedientes judiciales. Los resultados señalan la justificación de la utilización del encierro en el ordenamiento de la cotidianidad adolescente, así como las consecuencias que la privación de libertad deja impresa en los jóvenes, analizadas mediante prácticas profesionales en medio abierto. Las conclusiones plantean la tensión aun existente entre castigo y protección social en discursos divergentes acerca de las medidas reguladoras de la transgresión normativa.