arXiv subjects

Harold Ship

Publications and source records attributed to Harold Ship.

4 recordsLinked to original sources

arXiv2026

Governance by Construction for Generalist Agents

Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by construction. Systems must specify which actions are allowed, when human oversight is required, and what information may be exposed, without rebuilding the agent for each domain. This demo presents CUGA's policy system, a modular policy-as-code layer that composes with a generalist LLM agent to deliver predictable, auditable, and compliance-aware behavior in compound workflows without model fine-tuning. We present a runtime governance architecture that enforces policy interventions at every critical stage of execution. Rather than passively constraining behavior, policies intercept the agent at five structural checkpoints: upstream of planning (Intent Guard), within the system prompt to steer reasoning (Playbook), at the tool-call boundary to enforce proper usage (Tool Guide), outside the reasoning loop as a Human-in-the-Loop gate for high-risk actions (Tool Approvals), and at the output stage to filter and structure the final response (Output Formatter). Together, these stages embed governance continuously across the agent's execution pipeline rather than treating it as an afterthought. Using a healthcare scenario and a multi-layered enforcement intervention, the demo shows dynamic playbook injection for structured tool-sequence enforcement, intent guards that block malicious or accidental harmful requests, and human-in-the-loop tool approval checkpoints for potentially destructive actions. The artifact illustrates how typed governance primitives enable faster, safer deployment of enterprise agentic systems while improving policy adherence and execution consistency.

cs.AI↗

arXiv2023

Optimizing simultaneous autoscaling for serverless cloud computing

This paper explores resource allocation in serverless cloud computing platforms and proposes an optimization approach for autoscaling systems. Serverless computing relieves users from resource management tasks, enabling focus on application functions. However, dynamic resource allocation and function replication based on changing loads remain crucial. Typically, autoscalers in these platforms utilize threshold-based mechanisms to adjust function replicas independently. We model applications as interconnected graphs of functions, where requests probabilistically traverse the graph, triggering associated function execution. Our objective is to develop a control policy that optimally allocates resources on servers, minimizing failed requests and response time in reaction to load changes. Using a fluid approximation model and Separated Continuous Linear Programming (SCLP), we derive an optimal control policy that determines the number of resources per replica and the required number of replicas over time. We evaluate our approach using a simulation framework built with Python and simpy. Comparing against threshold-based autoscaling, our approach demonstrates significant improvements in average response times and failed requests, ranging from 15% to over 300% in most cases. We also explore the impact of system and workload parameters on performance, providing insights into the behavior of our optimization approach under different conditions. Overall, our study contributes to advancing resource allocation strategies, enhancing efficiency and reliability in serverless cloud computing platforms.

cs.DC↗

arXiv2022

A Robust Server-Effort Policy for Fluid Processing Networks

Multi-Class Processing Networks describe a set of servers that perform multiple classes of jobs on different items. A useful and tractable way to find an optimal control for such a network is to approximate it by a fluid model, resulting in a Separated Continuous Linear Programming (SCLP) problem. Clearly, arrival and service rates in such systems suffer from inherent uncertainty. A recent study addressed this issue by formulating a Robust Counterpart for SCLP models with budgeted uncertainty which provides a solution in terms of processing rates. This solution is transformed into a sequencing policy. However, in cases where servers can process several jobs simultaneously, a sequencing policy cannot be implemented. In this paper, we propose to use in these cases a a resource allocation policy, namely, the proportion of server effort per class. We formulate Robust Counterparts of both processing rates and server-effort uncertain models for four types of uncertainty sets: box, budgeted, one-sided budgeted, and polyhedral. We prove that server-effort model provides a better robust solution than any algebraic transformation of the robust solution of the processing rates model. Finally, to get a grasp of how much our new model improves over the processing rates robust model, we provide results of some numerical experiments.

math.OC↗

arXiv2019

Separable nonlinear least-squares parameter estimation for complex dynamic systems

Nonlinear dynamic models are widely used for characterizing functional forms of processes that govern complex biological pathway systems. Over the past decade, validation and further development of these models became possible due to data collected via high-throughput experiments using methods from molecular biology. While these data are very beneficial, they are typically incomplete and noisy, so that inferring parameter values for complex dynamic models is associated with serious computational challenges. Fortunately, many biological systems have embedded linear mathematical features, which may be exploited, thereby improving fits and leading to better convergence of optimization algorithms. In this paper, we explore options of inference for dynamic models using a novel method of {\it separable nonlinear least-squares optimization}, and compare its performance to the traditional nonlinear least-squares method. The numerical results from extensive simulations suggest that the proposed approach is at least as accurate as the traditional nonlinear least-squares, but usually superior, while also enjoying a substantial reduction in computational time.

stat.ME↗