8 papers
The Price of Feasibility: Greedy Approximation Bounds for String Supermodular Optimization over Oracle-Conditioned Greedoids
Joan Vendrell Gallart, Russell Bent, Solmaz Kia
Greedy algorithms efficiently approximate combinatorial optimization problems, but their guarantees weaken when feasibility couples combinatorial structure with global physical con…
An Agentic Orchestration of Atomistic Simulations
Rahul Somasundaram, Adela Habib, Khanh Dang +12
Atomistic simulations are central to materials design, but their execution involves complex, multi-step workflows that require significant human expertise. Here, we present an agen…
Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction
Joan Vendrell Gallart, Solmaz Kia, Russell Bent +1
We introduce CAROL (Chain-based Adaptive Reconfiguration Over Lattices), a probabilistic framework for test-time hallucination reduction in large language models. Rather than relyi…
Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models
Joan Vendrell Gallart, Russell Bent, Michael Grosskopf
Large Language Models are increasingly deployed inside agentic systems, where they must follow structured protocols, adapt to evolving states, and operate under memory, latency, an…
Microgrids optimal radial reconfiguration via FORWARD algorithm
Joan Vendrell Gallart, Russell Bent, Solmaz Kia
Microgrids offer a promising paradigm for integrating distributed energy resources, bolstering energy resilience, and reducing the impact of blackouts. However, their inherent dece…
FORWARD: A Feasible Radial Reconfiguration Algorithm for Multi-Source Distribution Networks
Joan Vendrell Gallart, Russell Bent, Solmaz Kia
This paper considers an optimal radial reconfiguration problem in multi-source distribution networks, where the goal is to find a radial configuration that minimizes quadratic dist…
URSA: The Universal Research and Scientific Agent
Michael Grosskopf, Nathan Debardeleben, Russell Bent +10
Large language models (LLMs) have moved far beyond their initial form as simple chatbots, now carrying out complex reasoning, planning, writing, coding, and research tasks. These s…
FORWARD: Feasibility Oriented Random-Walk Inspired Algorithm for Radial Reconfiguration in Distribution Networks
Joan Vendrell, Russell Bent, Solmaz Kia
We consider an optimal flow distribution problem in which the goal is to find a radial configuration that minimizes resistance-induced quadratic distribution costs while ensuring d…