Peter A. Beling

Lanxiao Huang, Tyler Cody, Christopher Redino et al.

Reinforcement learning (RL) operating on attack graphs leveraging cyber terrain principles are used to develop reward and state associated with determination of surveillance detection routes (SDR). This work extends previous efforts on developing RL methods for path analysis within enterprise networks. This work focuses on building SDR where the routes focus on exploring the network services while trying to evade risk. RL is utilized to support the development of these routes by building a reward mechanism that would help in realization of these paths. The RL algorithm is modified to have a novel warm-up phase which decides in the initial exploration which areas of the network are safe to explore based on the rewards and penalty scale factor.

Tyler Cody, Niloofar Shadab, Alejandro Salado et al.

Engineering methods are centered around traditional notions of decomposition and recomposition that rely on partitioning the inputs and outputs of components to allow for component-level properties to hold after their composition. In artificial intelligence (AI), however, systems are often expected to influence their environments, and, by way of their environments, to influence themselves. Thus, it is unclear if an AI system's inputs will be independent of its outputs, and, therefore, if AI systems can be treated as traditional components. This paper posits that engineering general intelligence requires new general systems precepts, termed the core and periphery, and explores their theoretical uses. The new precepts are elaborated using abstract systems theory and the Law of Requisite Variety. By using the presented material, engineers can better understand the general character of regulating the outcomes of AI to achieve stakeholder needs and how the general systems nature of embodiment challenges traditional engineering practice.

Niloofar Shadab, Tyler Cody, Alejandro Salado et al.

There is a lack of formalism for some key foundational concepts in systems engineering. One of the most recently acknowledged deficits is the inadequacy of systems engineering practices for engineering intelligent systems. In our previous works, we proposed that closed systems precepts could be used to accomplish a required paradigm shift for the systems engineering of intelligent systems. However, to enable such a shift, formal foundations for closed systems precepts that expand the theory of systems engineering are needed. The concept of closure is a critical concept in the formalism underlying closed systems precepts. In this paper, we provide formal, systems- and information-theoretic definitions of closure to identify and distinguish different types of closed systems. Then, we assert a mathematical framework to evaluate the subjective formation of the boundaries and constraints of such systems. Finally, we argue that engineering an intelligent system can benefit from appropriate closed and open systems paradigms on multiple levels of abstraction of the system. In the main, this framework will provide the necessary fundamentals to aid in systems engineering of intelligent systems.

Sai Prathyush Katragadda, Tyler Cody, Peter Beling et al.

Active learning is a practical field of machine learning that automates the process of selecting which data to label. Current methods are effective in reducing the burden of data labeling but are heavily model-reliant. This has led to the inability of sampled data to be transferred to new models as well as issues with sampling bias. Both issues are of crucial concern in machine learning deployment. We propose active learning methods utilizing combinatorial coverage to overcome these issues. The proposed methods are data-centric, as opposed to model-centric, and through our experiments we show that the inclusion of coverage in active learning leads to sampling data that tends to be the best in transferring to better performing models and has a competitive sampling bias compared to benchmark methods.

Tuo Wang, Adithya Kulkarni, Tyler Cody et al.

Uncertainty estimation is essential for enhancing the reliability of Large Language Models (LLMs), particularly in high-stakes applications. Existing methods often overlook semantic dependencies, relying on token-level probability measures that fail to capture structural relationships within the generated text. We propose GENUINE: Graph ENhanced mUlti-level uncertaINty Estimation for Large Language Models, a structure-aware framework that leverages dependency parse trees and hierarchical graph pooling to refine uncertainty quantification. By incorporating supervised learning, GENUINE effectively models semantic and structural relationships, improving confidence assessments. Extensive experiments across NLP tasks show that GENUINE achieves up to 29% higher AUROC than semantic entropy-based approaches and reduces calibration errors by over 15%, demonstrating the effectiveness of graph-based uncertainty modeling. The code is available at https://github.com/ODYSSEYWT/GUQ.

Tyler Cody, Bingtong Li, Peter A. Beling

This paper addresses the urgent need for messaging standards in the operational test and evaluation (T&E) of machine learning (ML) applications, particularly in edge ML applications embedded in systems like robots, satellites, and unmanned vehicles. It examines the suitability of the IEEE Standard 1671 (IEEE Std 1671), known as the Automatic Test Markup Language (ATML), an XML-based standard originally developed for electronic systems, for ML application testing. The paper explores extending IEEE Std 1671 to encompass the unique challenges of ML applications, including the use of datasets and dependencies on software. Through modeling various tests such as adversarial robustness and drift detection, this paper offers a framework adaptable to specific applications, suggesting that minor modifications to ATML might suffice to address the novelties of ML. This paper differentiates ATML's focus on testing from other ML standards like Predictive Model Markup Language (PMML) or Open Neural Network Exchange (ONNX), which concentrate on ML model specification. We conclude that ATML is a promising tool for effective, near real-time operational T&E of ML applications, an essential aspect of AI lifecycle management, safety, and governance.

Anli du Preez, Peter A. Beling, Tyler Cody

The machine learning formulation of online learning is incomplete from a systems theoretic perspective. Typically, machine learning research emphasizes domains and tasks, and a problem solving worldview. It focuses on algorithm parameters, features, and samples, and neglects the perspective offered by considering system structure and system behavior or dynamics. Online learning is an active field of research and has been widely explored in terms of statistical theory and computational algorithms, however, in general, the literature still lacks formal system theoretical frameworks for modeling online learning systems and resolving systems-related concept drift issues. Furthermore, while the machine learning formulation serves to classify methods and literature, the systems theoretic formulation presented herein serves to provide a framework for the top-down design of online learning systems, including a novel definition of online learning and the identification of key design parameters. The framework is formulated in terms of input-output systems and is further divided into system structure and system behavior. Concept drift is a critical challenge faced in online learning, and this work formally approaches it as part of the system behavior characteristics. Healthcare provider fraud detection using machine learning is used as a case study throughout the paper to ground the discussion in a real-world online learning challenge.

Lanxiao Huang, Daksh Dave, Tyler Cody et al.

Large language models (LLMs) are increasingly used to automate or augment penetration testing, but their effectiveness and reliability across attack phases remain unclear. We present a comprehensive evaluation of multiple LLM-based agents, from single-agent to modular designs, across realistic penetration testing scenarios, measuring empirical performance and recurring failure patterns. We also isolate the impact of five core functional capabilities via targeted augmentations: Global Context Memory (GCM), Inter-Agent Messaging (IAM), Context-Conditioned Invocation (CCI), Adaptive Planning (AP), and Real-Time Monitoring (RTM). These interventions support, respectively: (i) context coherence and retention, (ii) inter-component coordination and state management, (iii) tool use accuracy and selective execution, (iv) multi-step strategic planning, error detection, and recovery, and (v) real-time dynamic responsiveness. Our results show that while some architectures natively exhibit subsets of these properties, targeted augmentations substantially improve modular agent performance, especially in complex, multi-step, and real-time penetration testing tasks.

Niloofar Shadab, Tyler Cody, Alejandro Salado et al.

Engineering methodologies predominantly revolve around established principles of decomposition and recomposition. These principles involve partitioning inputs and outputs at the component level, ensuring that the properties of individual components are preserved upon composition. However, this view does not transfer well to intelligent systems, particularly when addressing the scaling of intelligence as a system property. Our prior research contends that the engineering of general intelligence necessitates a fresh set of overarching systems principles. As a result, we introduced the "core and periphery" principles, a novel conceptual framework rooted in abstract systems theory and the Law of Requisite Variety. In this paper, we assert that these abstract concepts hold practical significance. Through empirical evidence, we illustrate their applicability to both biological and artificial intelligence systems, bridging abstract theory with real-world implementations. Then, we expand on our previous theoretical framework by mathematically defining core-dominant vs periphery-dominant systems.

Tyler Cody, Abdul Rahman, Christopher Redino et al.

Reinforcement learning (RL), in conjunction with attack graphs and cyber terrain, are used to develop reward and state associated with determination of optimal paths for exfiltration of data in enterprise networks. This work builds on previous crown jewels (CJ) identification that focused on the target goal of computing optimal paths that adversaries may traverse toward compromising CJs or hosts within their proximity. This work inverts the previous CJ approach based on the assumption that data has been stolen and now must be quietly exfiltrated from the network. RL is utilized to support the development of a reward function based on the identification of those paths where adversaries desire reduced detection. Results demonstrate promising performance for a sizable network environment.

Mark Rucker, Stephen Adams, Roy Hayes et al.

In adversarial environments, one side could gain an advantage by identifying the opponent's strategy. For example, in combat games, if an opponents strategy is identified as overly aggressive, one could lay a trap that exploits the opponent's aggressive nature. However, an opponent's strategy is not always apparent and may need to be estimated from observations of their actions. This paper proposes to use inverse reinforcement learning (IRL) to identify strategies in adversarial environments. Specifically, the contributions of this work are 1) the demonstration of this concept on gaming combat data generated from three pre-defined strategies and 2) the framework for using IRL to achieve strategy identification. The numerical experiments demonstrate that the recovered rewards can be identified using a variety of techniques. In this paper, the recovered reward are visually displayed, clustered using unsupervised learning, and classified using a supervised learner.

Tyler Cody, Peter A. Beling

Existing frameworks for transfer learning are incomplete from a systems theoretic perspective. They place emphasis on notions of domain and task, and neglect notions of structure and behavior. In doing so, they limit the extent to which formalism can be carried through into the elaboration of their frameworks. Herein, we use Mesarovician systems theory to define transfer learning as a relation on sets and subsequently characterize the general nature of transfer learning as a mathematical construct. We interpret existing frameworks in terms of ours and go beyond existing frameworks to define notions of transferability, transfer roughness, and transfer distance. Importantly, despite its formalism, our framework avoids the detailed mathematics of learning theory or machine learning solution methods without excluding their consideration. As such, we provide a formal, general systems framework for modeling transfer learning that offers a rigorous foundation for system design and analysis.

Tyler Cody, Stephen Adams, Peter A. Beling

Classical machine learning approaches are sensitive to non-stationarity. Transfer learning can address non-stationarity by sharing knowledge from one system to another, however, in areas like machine prognostics and defense, data is fundamentally limited. Therefore, transfer learning algorithms have little, if any, examples from which to learn. Herein, we suggest that these constraints on algorithmic learning can be addressed by systems engineering. We formally define transfer distance in general terms and demonstrate its use in empirically quantifying the transferability of models. We consider the use of transfer distance in the design of machine rebuild procedures to allow for transferable prognostic models. We also consider the use of transfer distance in predicting operational performance in computer vision. Practitioners can use the presented methodology to design and operate systems with consideration for the learning theoretic challenges faced by component learning systems.

Jianyu Su, Stephen Adams, Peter A. Beling

The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance, by far, on multi-agent benchmarks, StarCraft II micromanagement tasks. However, our experiments show that, in some cases, QMIX is incompatible with A2C, a training paradigm that promotes algorithm training efficiency. To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decomposition to actor-critics that are compatible with A2C and propose a novel actor-critic framework, value-decomposition actor-critics (VDACs). We evaluate VDACs on the testbed of StarCraft II micromanagement tasks and demonstrate that the proposed framework improves median performance over other actor-critic methods. Furthermore, we use a set of ablation experiments to identify the key factors that contribute to the performance of VDACs.

Jianyu Su, Stephen Adams, Peter A. Beling

We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment. We propose that multi-agent systems must have the ability to (1) communicate and understand the inter-plays between agents and (2) correctly distribute rewards based on an individual agent's contribution. In contrast, most work in this setting considers only one of the above abilities. In this study, we develop an architecture that allows for communication among agents and tailors the system's reward for each individual agent. Our architecture represents agent communication through graph convolution and applies an existing credit assignment structure, counterfactual multi-agent policy gradient (COMA), to assist agents to learn communication by back-propagation. The flexibility of the graph structure enables our method to be applicable to a variety of multi-agent systems, e.g. dynamic systems that consist of varying numbers of agents and static systems with a fixed number of agents. We evaluate our method on a range of tasks, demonstrating the advantage of marrying communication with credit assignment. In the experiments, our proposed method yields better performance than the state-of-art methods, including COMA. Moreover, we show that the communication strategies offers us insights and interpretability of the system's cooperative policies.

Jianyu Su, Peter A. Beling, Rui Guo et al.

The ability to model and predict ego-vehicle's surrounding traffic is crucial for autonomous pilots and intelligent driver-assistance systems. Acceleration prediction is important as one of the major components of traffic prediction. This paper proposes novel approaches to the acceleration prediction problem. By representing spatial relationships between vehicles with a graph model, we build a generalized acceleration prediction framework. This paper studies the effectiveness of proposed Graph Convolution Networks, which operate on graphs predicting the acceleration distribution for vehicles driving on highways. We further investigate prediction improvement through integrating of Recurrent Neural Networks to disentangle the temporal complexity inherent in the traffic data. Results from simulation studies using comprehensive performance metrics support the conclusion that our proposed networks outperform state-of-the-art methods in generating realistic trajectories over a prediction horizon.

Xiaomin Lin, Peter A. Beling, Randy Cogill

We compare the performance of Inverse Reinforcement Learning (IRL) with the relative new model of Multi-agent Inverse Reinforcement Learning (MIRL). Before comparing the methods, we extend a published Bayesian IRL approach that is only applicable to the case where the reward is only state dependent to a general one capable of tackling the case where the reward depends on both state and action. Comparison between IRL and MIRL is made in the context of an abstract soccer game, using both a game model in which the reward depends only on state and one in which it depends on both state and action. Results suggest that the IRL approach performs much worse than the MIRL approach. We speculate that the underperformance of IRL is because it fails to capture equilibrium information in the manner possible in MIRL.

Xiaomin Lin, Peter A. Beling, Randy Cogill

The focus of this paper is a Bayesian framework for solving a class of problems termed multi-agent inverse reinforcement learning (MIRL). Compared to the well-known inverse reinforcement learning (IRL) problem, MIRL is formalized in the context of stochastic games, which generalize Markov decision processes to game theoretic scenarios. We establish a theoretical foundation for competitive two-agent zero-sum MIRL problems and propose a Bayesian solution approach in which the generative model is based on an assumption that the two agents follow a minimax bi-policy. Numerical results are presented comparing the Bayesian MIRL method with two existing methods in the context of an abstract soccer game. Investigation centers on relationships between the extent of prior information and the quality of learned rewards. Results suggest that covariance structure is more important than mean value in reward priors.

Qifeng Qiao, Peter A. Beling

We propose a multiple instance learning approach to content-based retrieval of classroom video for the purpose of supporting human assessing the learning environment. The key element of our approach is a mapping between the semantic concepts of the assessment system and features of the video that can be measured using techniques from the fields of computer vision and speech analysis. We report on a formative experiment in content-based video retrieval involving trained experts in the Classroom Assessment Scoring System, a widely used framework for assessment and improvement of learning environments. The results of this experiment suggest that our approach has potential application to productivity enhancement in assessment and to broader retrieval tasks.

Roy Hayes, Peter Beling, William Scherer

Real Time Strategy (RTS) games provide complex domain to test the latest artificial intelligence (AI) research. In much of the literature, AI systems have been limited to playing one game. Although, this specialization has resulted in stronger AI gaming systems it does not address the key concerns of AI researcher. AI researchers seek the development of AI agents that can autonomously interpret learn, and apply new knowledge. To achieve human level performance, current AI systems rely on game specific knowledge of an expert. The paper presents the full RTS language in hopes of shifting the current research focus to the development of general RTS agents. General RTS agents are AI gaming systems that can play any RTS games, defined in the RTS language. This prevents game specific knowledge from being hard coded into the system, thereby facilitating research that addresses the fundamental concerns of artificial intelligence.

Qifeng Qiao, Peter A. Beling

We study the use of inverse reinforcement learning (IRL) as a tool for the recognition of agents' behavior on the basis of observation of their sequential decision behavior interacting with the environment. We model the problem faced by the agents as a Markov decision process (MDP) and model the observed behavior of the agents in terms of forward planning for the MDP. We use IRL to learn reward functions and then use these reward functions as the basis for clustering or classification models. Experimental studies with GridWorld, a navigation problem, and the secretary problem, an optimal stopping problem, suggest reward vectors found from IRL can be a good basis for behavior pattern recognition problems. Empirical comparisons of our method with several existing IRL algorithms and with direct methods that use feature statistics observed in state-action space suggest it may be superior for recognition problems.

Qifeng Qiao, Peter A. Beling

We present new algorithms for inverse reinforcement learning (IRL, or inverse optimal control) in convex optimization settings. We argue that finite-space IRL can be posed as a convex quadratic program under a Bayesian inference framework with the objective of maximum a posterior estimation. To deal with problems in large or even infinite state space, we propose a Gaussian process model and use preference graphs to represent observations of decision trajectories. Our method is distinguished from other approaches to IRL in that it makes no assumptions about the form of the reward function and yet it retains the promise of computationally manageable implementations for potential real-world applications. In comparison with an establish algorithm on small-scale numerical problems, our method demonstrated better accuracy in apprenticeship learning and a more robust dependence on the number of observations.